import pandas as pd
import numpy as np

# To help with data visualization
import matplotlib.pyplot as plt # data visualization
import seaborn as sns # data visualization
%matplotlib inline
sns.set_style('whitegrid') # set style for visualization

# To supress warnings
import warnings # ignore warnings
warnings.filterwarnings('ignore')

from scipy.stats import zscore

#normalizing
from sklearn.preprocessing import MinMaxScaler, StandardScaler, PolynomialFeatures # to scale the data

# modeling
import statsmodels.api as sm # adding a constant to the independent variables
from sklearn.model_selection import train_test_split # splitting data in train and test sets
from sklearn.preprocessing import PowerTransformer, StandardScaler # for normalization


from sklearn.linear_model import LinearRegression, Lasso, Ridge
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.svm import SVR

from sklearn.ensemble import RandomForestRegressor, GradientBoostingRegressor, StackingRegressor
from sklearn.neural_network import MLPRegressor
import xgboost as xgb
import lightgbm as lgb
#import catboost as catb
# CatBoost is a fast, scalable, high performance gradient boosting on decision trees library.
# Used for ranking, classification, regression and other ML tasks
# COULDN'T BE TESTED ON THIS PROJECT DUE ISSUES ON SETUP

from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score

#To check multicollinearity
from statsmodels.stats.outliers_influence import variance_inflation_factor

# To be used for tuning the model
from sklearn.model_selection import GridSearchCV, RandomizedSearchCV

# for validation
from sklearn.model_selection import cross_val_score, KFold, cross_validate

# Deploy
import joblib
import streamlit as st

import datetime
import os

df=pd.read_csv('DATA_Barcelona_Fotocasa_HousingPrices_Augmented.csv')

df.head() # preview a sample first 5 rows

df.tail() # preview a sample last 5 rows

df.sample(20) # preview a sample random n rows

print("There are", df.shape[0], 'rows and', df.shape[1], "columns.") # number of observations and features

There are 16376 rows and 10 columns.

df.dtypes # data types

Unnamed: 0               int64
price                    int64
rooms                  float64
bathroom               float64
lift                      bool
terrace                   bool
square_meters          float64
real_state              object
neighborhood            object
square_meters_price    float64
dtype: object

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 16376 entries, 0 to 16375
Data columns (total 10 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   Unnamed: 0           16376 non-null  int64  
 1   price                16376 non-null  int64  
 2   rooms                15966 non-null  float64
 3   bathroom             15989 non-null  float64
 4   lift                 16376 non-null  bool   
 5   terrace              16376 non-null  bool   
 6   square_meters        15968 non-null  float64
 7   real_state           15458 non-null  object 
 8   neighborhood         16376 non-null  object 
 9   square_meters_price  15937 non-null  float64
dtypes: bool(2), float64(4), int64(2), object(2)
memory usage: 1.0+ MB

df.describe(include="all").T # statistical summary of the data.

# Uniques
df.nunique() # Checking for number of variations in the data

Unnamed: 0             16376
price                    889
rooms                   1995
bathroom                1015
lift                       2
terrace                    2
square_meters           7751
real_state                 4
neighborhood              10
square_meters_price     9122
dtype: int64

df.columns

Index(['Unnamed: 0', 'price', 'rooms', 'bathroom', 'lift', 'terrace',
       'square_meters', 'real_state', 'neighborhood', 'square_meters_price'],
      dtype='object')

for i in ['rooms', 'bathroom', 'lift', 'terrace', 'real_state', 'neighborhood']: # Checking uniques
    print (i,": ",df[i].unique())

rooms :  [3.    2.    1.    ... 4.131 4.195 2.899]
bathroom :  [1.    2.    3.    ... 5.898 2.862 2.866]
lift :  [ True False]
terrace :  [False  True]
real_state :  ['flat' 'attic' nan 'apartment' 'study']
neighborhood :  ['Horta- Guinardo' 'Sant Andreu' 'Gràcia' 'Ciutat Vella'
 'Sarria-Sant Gervasi' 'Les Corts' 'Sant Martí' 'Eixample'
 'Sants-Montjuïc' 'Nou Barris']

# Uniques
cat_cols = df.select_dtypes(include=['category', 'object','bool']).columns.tolist()
for column in cat_cols:
    print(df[column].value_counts())
    print("-" * 50)

lift
True     11246
False     5130
Name: count, dtype: int64
--------------------------------------------------
terrace
False    12770
True      3606
Name: count, dtype: int64
--------------------------------------------------
real_state
flat         12650
apartment     1967
attic          633
study          208
Name: count, dtype: int64
--------------------------------------------------
neighborhood
Eixample               4795
Sarria-Sant Gervasi    2765
Ciutat Vella           2716
Gràcia                 1416
Sant Martí             1257
Sants-Montjuïc         1165
Les Corts              1045
Horta- Guinardo         638
Sant Andreu             368
Nou Barris              211
Name: count, dtype: int64
--------------------------------------------------

# Display all rows in pandas outputs
pd.set_option("display.max_rows", None)  # Set to None to show all rows

# Print the value counts of 'rooms'
print(df['rooms'].value_counts())
print("-" * 50)
print(df['bathroom'].value_counts())

# Optionally reset display settings (if needed later in the script)
pd.reset_option("display.max_rows")

rooms
2.000     2608
3.000     2461
1.000     1600
4.000     1061
0.000      399
5.000      232
6.000       28
0.910       19
0.981       15
1.029       14
0.945       14
0.917       14
1.973       13
1.012       13
0.938       13
1.076       13
1.804       12
1.872       12
0.937       12
0.956       12
3.046       12
1.954       12
1.087       12
2.119       12
2.056       12
1.046       12
2.004       12
1.904       12
1.015       12
2.126       12
0.947       12
1.882       12
1.840       12
2.122       11
1.095       11
1.897       11
3.017       11
3.237       11
1.008       11
1.884       11
2.169       11
2.153       11
2.156       11
2.147       11
0.914       11
1.072       11
0.990       11
1.042       11
2.123       11
1.898       11
2.196       11
1.981       11
0.926       11
1.092       11
1.056       11
1.952       11
2.072       11
0.921       11
2.030       10
1.088       10
1.865       10
2.192       10
1.917       10
0.970       10
2.068       10
1.051       10
0.971       10
0.919       10
2.084       10
1.069       10
1.948       10
1.082       10
2.027       10
1.021       10
2.152       10
3.292       10
2.160       10
2.019       10
1.949       10
0.932       10
2.011       10
1.887       10
1.080       10
1.940       10
0.934       10
2.168       10
2.089       10
1.877       10
2.985       10
0.987       10
2.107       10
1.048       10
1.823       10
1.099       10
0.902       10
0.950       10
1.960       10
0.995       10
2.913       10
0.973       10
1.083       10
2.137       10
1.043       10
1.824       10
1.098       10
1.079        9
2.157        9
1.027        9
0.948        9
2.148        9
2.049        9
2.124        9
2.959        9
0.965        9
2.103        9
1.024        9
2.106        9
1.070        9
0.998        9
1.035        9
1.932        9
0.906        9
2.038        9
1.017        9
0.904        9
0.992        9
0.943        9
1.855        9
2.082        9
2.023        9
1.926        9
1.936        9
2.032        9
1.883        9
1.868        9
1.837        9
1.041        9
0.961        9
1.016        9
1.996        9
1.967        9
1.867        9
3.090        9
2.145        9
2.026        9
2.101        9
1.841        9
1.902        9
0.968        9
1.084        9
0.994        9
1.931        8
1.007        8
1.990        8
1.060        8
2.130        8
3.037        8
1.854        8
2.131        8
1.835        8
2.076        8
1.875        8
0.927        8
0.983        8
0.930        8
2.075        8
2.115        8
2.796        8
1.803        8
3.065        8
1.064        8
1.002        8
1.011        8
1.953        8
0.916        8
2.748        8
1.966        8
1.014        8
1.074        8
2.060        8
3.097        8
1.019        8
3.073        8
1.833        8
3.284        8
2.007        8
2.161        8
2.081        8
2.723        8
0.996        8
2.034        8
0.925        8
2.945        8
3.157        8
0.911        8
2.858        8
0.969        8
2.817        8
1.971        8
1.010        8
1.836        8
2.028        8
1.068        8
1.958        8
1.089        8
2.708        8
2.163        8
3.081        8
0.942        8
1.974        8
0.975        8
1.832        8
2.777        8
2.195        8
1.876        8
2.046        8
0.952        8
2.979        8
0.922        8
0.940        8
3.039        8
2.150        8
1.033        8
2.154        8
2.093        8
1.853        8
2.102        8
1.901        8
1.888        8
2.045        8
1.045        8
1.944        8
2.170        8
0.931        8
0.957        8
1.905        8
0.955        8
2.722        8
1.961        7
2.051        7
1.822        7
2.857        7
2.043        7
0.903        7
1.957        7
0.933        7
2.139        7
2.158        7
2.999        7
2.118        7
2.167        7
2.978        7
0.989        7
1.026        7
3.164        7
0.966        7
3.226        7
1.863        7
2.977        7
3.222        7
1.075        7
0.980        7
0.964        7
2.191        7
1.864        7
1.030        7
2.090        7
2.175        7
0.959        7
2.188        7
1.847        7
3.297        7
0.958        7
2.725        7
3.055        7
2.035        7
0.913        7
1.922        7
2.931        7
2.794        7
2.149        7
1.989        7
1.927        7
2.903        7
2.077        7
1.992        7
1.061        7
1.977        7
2.848        7
3.271        7
2.050        7
2.129        7
0.915        7
3.078        7
2.003        7
2.846        7
1.073        7
1.893        7
2.906        7
2.033        7
2.198        7
2.116        7
1.965        7
2.080        7
1.978        7
1.895        7
0.972        7
1.984        7
0.908        7
1.044        7
1.845        7
2.132        7
2.952        7
3.154        7
0.954        7
1.993        7
2.031        7
1.852        7
2.938        7
3.253        7
0.912        7
2.870        7
1.851        7
1.055        7
1.006        7
2.924        7
0.924        7
1.808        7
2.184        7
1.071        7
2.048        7
2.044        7
1.930        7
1.968        7
0.900        7
2.117        7
2.136        7
2.173        7
1.821        7
1.090        7
1.900        7
2.001        7
3.019        7
2.738        7
2.092        7
3.283        7
2.059        7
3.249        7
2.087        6
2.159        6
1.096        6
1.093        6
2.937        6
2.114        6
2.715        6
2.882        6
0.939        6
0.991        6
2.165        6
2.143        6
1.939        6
2.815        6
1.830        6
3.242        6
1.850        6
2.095        6
2.021        6
2.710        6
1.031        6
2.070        6
2.073        6
2.934        6
3.227        6
1.941        6
2.015        6
2.957        6
3.035        6
2.933        6
3.075        6
3.113        6
1.916        6
3.193        6
2.199        6
3.076        6
2.872        6
1.985        6
2.134        6
3.229        6
2.037        6
2.727        6
2.025        6
3.214        6
1.022        6
2.171        6
1.081        6
2.125        6
1.003        6
2.066        6
3.186        6
0.976        6
2.008        6
3.200        6
1.995        6
1.947        6
3.184        6
2.871        6
1.059        6
2.190        6
2.078        6
2.020        6
2.873        6
1.870        6
3.232        6
2.058        6
2.009        6
3.011        6
3.295        6
2.146        6
2.717        6
3.028        6
2.981        6
2.916        6
1.911        6
3.060        6
1.983        6
1.050        6
1.918        6
2.901        6
2.879        6
3.063        6
3.111        6
0.982        6
2.897        6
3.199        6
1.814        6
2.110        6
0.979        6
2.052        6
2.874        6
1.912        6
1.987        6
1.086        6
1.924        6
1.020        6
3.258        6
3.285        6
1.805        6
0.999        6
2.724        6
1.970        6
3.062        6
3.250        6
1.935        6
2.702        6
3.102        6
1.058        6
0.918        6
2.111        6
1.857        6
2.094        6
3.212        6
3.106        6
0.978        6
2.926        6
0.923        6
1.025        6
2.109        6
0.993        6
2.914        6
2.186        6
2.920        6
1.878        6
0.909        6
1.807        6
2.909        6
2.865        6
2.818        6
2.967        6
0.944        6
3.276        6
1.077        6
1.998        6
2.057        6
3.101        6
1.903        6
0.920        6
1.963        6
2.753        6
0.974        6
3.032        6
2.884        6
2.179        6
2.144        6
1.834        6
3.187        6
1.909        6
1.001        6
2.140        6
2.141        6
2.984        6
2.755        6
0.946        6
3.167        6
1.925        6
1.946        6
1.915        6
2.987        6
2.771        5
3.079        5
3.004        5
2.013        5
2.843        5
3.027        5
2.786        5
1.950        5
3.231        5
1.910        5
2.894        5
3.206        5
2.844        5
2.182        5
2.811        5
3.020        5
3.235        5
1.886        5
3.260        5
3.010        5
3.275        5
1.034        5
1.933        5
1.818        5
3.183        5
2.836        5
1.032        5
2.164        5
1.856        5
2.955        5
3.122        5
3.191        5
2.054        5
3.262        5
3.131        5
3.224        5
3.100        5
1.980        5
3.080        5
3.054        5
1.879        5
1.067        5
1.085        5
3.072        5
3.266        5
2.964        5
2.759        5
1.053        5
2.183        5
4.313        5
3.259        5
1.844        5
2.071        5
2.024        5
1.094        5
2.973        5
3.192        5
2.742        5
2.041        5
2.121        5
2.187        5
1.066        5
1.962        5
2.714        5
3.074        5
3.086        5
3.013        5
3.103        5
1.091        5
1.810        5
3.149        5
1.866        5
3.208        5
1.859        5
2.826        5
1.999        5
1.052        5
0.967        5
3.096        5
1.956        5
1.848        5
2.172        5
2.974        5
3.105        5
2.181        5
1.040        5
1.826        5
1.889        5
3.050        5
2.837        5
3.196        5
2.734        5
4.073        5
2.104        5
1.945        5
2.042        5
2.713        5
1.921        5
2.197        5
1.063        5
2.902        5
3.967        5
1.896        5
1.827        5
2.047        5
4.148        5
2.740        5
1.801        5
0.985        5
2.892        5
2.016        5
3.077        5
2.155        5
1.817        5
1.815        5
3.296        5
2.820        5
3.233        5
2.002        5
2.930        5
3.132        5
2.994        5
1.018        5
4.248        5
0.953        5
0.960        5
2.766        5
3.007        5
2.765        5
2.856        5
3.637        5
0.986        5
4.061        5
4.187        5
1.065        5
2.128        5
3.291        5
3.142        5
2.904        5
2.828        5
0.907        5
3.139        5
3.091        5
3.255        5
2.950        5
2.757        5
2.830        5
1.057        5
2.086        5
4.380        5
1.880        5
4.080        5
4.040        5
2.835        5
2.743        5
3.153        5
1.861        5
3.716        5
3.228        5
2.810        5
3.201        5
2.797        5
3.158        5
2.961        5
2.113        5
2.782        5
1.037        5
2.813        5
2.732        5
2.962        5
3.254        5
2.839        5
1.890        5
2.018        5
1.934        5
2.996        5
3.023        5
2.887        5
1.994        5
2.863        5
2.142        5
2.911        5
2.166        5
2.105        5
0.977        5
1.825        5
2.718        5
3.202        5
1.988        5
0.988        5
3.216        5
3.832        5
0.997        5
1.862        5
3.094        5
1.873        5
1.054        5
2.063        5
3.272        5
0.929        5
2.085        5
3.236        5
2.949        5
3.095        5
7.000        5
2.006        4
3.163        4
3.156        4
1.806        4
3.175        4
2.960        4
3.256        4
1.846        4
3.058        4
2.896        4
1.943        4
2.709        4
2.733        4
2.970        4
2.854        4
1.891        4
3.210        4
2.980        4
3.197        4
2.919        4
4.038        4
3.114        4
2.180        4
2.735        4
2.941        4
2.079        4
2.022        4
2.991        4
1.907        4
2.069        4
1.005        4
3.119        4
3.261        4
2.728        4
2.193        4
2.814        4
1.991        4
1.858        4
1.062        4
2.138        4
3.069        4
3.179        4
3.979        4
3.067        4
3.066        4
3.022        4
2.889        4
2.726        4
2.133        4
3.223        4
1.894        4
3.088        4
3.002        4
3.273        4
2.739        4
2.040        4
3.247        4
2.014        4
3.279        4
3.949        4
3.152        4
1.811        4
2.784        4
2.189        4
3.246        4
1.843        4
3.150        4
2.780        4
2.791        4
2.886        4
3.136        4
4.310        4
2.730        4
2.940        4
2.763        4
1.951        4
3.051        4
1.885        4
2.816        4
3.252        4
2.792        4
2.838        4
0.963        4
4.162        4
3.180        4
1.871        4
3.278        4
1.942        4
3.143        4
3.036        4
2.012        4
3.815        4
1.800        4
2.790        4
4.003        4
1.009        4
3.209        4
2.809        4
3.173        4
2.731        4
1.047        4
2.898        4
1.036        4
1.829        4
2.928        4
3.006        4
1.923        4
3.159        4
3.198        4
3.708        4
2.769        4
3.146        4
3.241        4
0.941        4
3.181        4
2.135        4
2.869        4
2.888        4
2.751        4
4.273        4
3.093        4
3.274        4
3.195        4
2.711        4
3.047        4
2.921        4
1.955        4
3.194        4
3.294        4
2.963        4
2.064        4
3.213        4
1.928        4
3.085        4
1.831        4
2.747        4
2.127        4
2.067        4
2.841        4
3.161        4
1.820        4
2.120        4
3.280        4
2.055        4
2.062        4
2.065        4
2.877        4
3.731        4
2.893        4
4.356        4
1.969        4
3.830        4
2.767        4
0.984        4
2.083        4
3.238        4
2.875        4
3.188        4
3.127        4
3.029        4
2.754        4
1.899        4
3.057        4
2.761        4
2.029        4
3.108        4
2.825        4
2.900        4
3.838        4
4.096        4
1.938        4
1.100        4
1.964        4
1.812        4
3.185        4
3.263        4
3.061        4
3.290        4
2.750        4
1.920        4
3.008        4
3.162        4
3.130        4
1.937        4
2.942        4
0.901        4
2.885        4
3.071        4
1.838        4
4.338        4
2.864        4
2.746        4
1.842        4
2.800        4
3.629        4
2.108        4
2.005        4
3.087        4
3.230        4
3.024        4
1.906        4
3.003        4
3.041        4
2.799        4
0.962        4
3.125        4
2.783        4
3.021        4
2.929        4
1.869        4
1.049        4
2.074        3
2.091        3
3.082        3
3.958        3
0.935        3
2.925        3
2.958        3
1.982        3
1.004        3
2.822        3
3.245        3
2.922        3
4.105        3
3.805        3
3.044        3
3.664        3
4.394        3
2.908        3
2.174        3
2.772        3
4.670        3
3.655        3
3.888        3
2.098        3
1.849        3
4.054        3
1.802        3
3.092        3
2.868        3
3.141        3
3.268        3
3.083        3
3.070        3
3.243        3
3.178        3
3.204        3
0.949        3
4.391        3
4.304        3
3.687        3
2.721        3
3.277        3
2.716        3
1.972        3
3.211        3
2.736        3
3.609        3
3.016        3
3.172        3
3.014        3
2.983        3
2.850        3
3.915        3
3.667        3
4.363        3
3.649        3
3.607        3
2.997        3
3.138        3
2.010        3
2.833        3
3.084        3
2.831        3
1.828        3
3.975        3
2.847        3
2.749        3
2.932        3
4.081        3
4.299        3
1.913        3
2.805        3
3.009        3
2.917        3
1.979        3
3.680        3
2.927        3
3.795        3
3.155        3
2.756        3
2.185        3
4.296        3
3.723        3
4.223        3
2.993        3
3.905        3
2.855        3
4.287        3
2.982        3
2.876        3
4.058        3
2.770        3
5.415        3
4.378        3
2.781        3
2.764        3
4.359        3
2.968        3
2.861        3
3.281        3
1.819        3
3.299        3
1.028        3
5.087        3
3.955        3
4.044        3
1.914        3
3.205        3
4.360        3
4.279        3
4.259        3
4.126        3
3.165        3
2.017        3
2.776        3
3.110        3
3.909        3
1.908        3
0.905        3
2.972        3
4.158        3
2.151        3
3.928        3
2.812        3
2.706        3
3.219        3
2.752        3
3.112        3
3.792        3
1.816        3
2.944        3
2.849        3
0.928        3
3.207        3
3.147        3
4.222        3
2.939        3
3.662        3
2.976        3
3.251        3
3.064        3
2.969        3
2.700        3
2.096        3
2.878        3
2.744        3
2.804        3
3.040        3
3.215        3
3.846        3
1.839        3
3.052        3
4.196        3
2.853        3
2.956        3
2.948        3
2.907        3
4.007        3
3.614        3
3.601        3
3.748        3
3.117        3
3.177        3
1.809        3
3.782        3
3.863        3
4.163        3
2.834        3
3.166        3
3.767        3
4.213        3
2.807        3
4.119        3
3.056        3
4.286        3
2.827        3
3.098        3
3.856        3
3.732        3
3.881        3
2.954        3
4.152        3
3.761        3
3.099        3
3.123        3
3.999        3
3.118        3
2.803        3
3.289        3
3.220        3
2.720        3
2.775        3
1.997        3
2.703        3
2.793        3
2.832        3
3.160        3
2.036        3
2.852        3
3.819        3
3.617        3
4.351        3
2.866        3
2.701        3
3.068        3
3.724        3
2.719        3
10.000       3
4.229        2
3.984        2
3.605        2
3.034        2
3.781        2
4.228        2
0.936        2
4.251        2
2.053        2
4.076        2
2.762        2
3.957        2
2.704        2
4.122        2
5.074        2
4.398        2
4.161        2
3.170        2
3.115        2
3.286        2
3.966        2
3.135        2
3.282        2
4.183        2
3.244        2
3.824        2
3.686        2
3.704        2
4.064        2
3.656        2
3.992        2
2.802        2
4.146        2
2.840        2
3.203        2
3.218        2
4.303        2
3.978        2
3.134        2
4.362        2
3.705        2
2.912        2
3.168        2
2.867        2
4.810        2
2.789        2
4.182        2
3.720        2
4.072        2
4.254        2
3.861        2
3.743        2
5.253        2
4.349        2
2.176        2
4.290        2
3.852        2
3.045        2
3.293        2
2.162        2
2.760        2
4.379        2
3.671        2
2.712        2
4.168        2
4.393        2
5.322        2
4.057        2
4.366        2
3.107        2
1.860        2
3.911        2
2.774        2
3.913        2
4.373        2
3.778        2
2.741        2
3.640        2
3.176        2
1.813        2
2.859        2
4.384        2
3.947        2
4.325        2
4.046        2
2.881        2
3.855        2
4.330        2
3.126        2
4.571        2
4.245        2
4.367        2
3.288        2
5.481        2
4.333        2
3.902        2
4.218        2
4.256        2
4.166        2
3.663        2
4.347        2
3.264        2
2.177        2
3.755        2
4.336        2
5.213        2
4.956        2
3.217        2
1.078        2
2.745        2
3.983        2
4.142        2
4.050        2
4.197        2
3.987        2
4.371        2
3.038        2
3.621        2
4.019        2
4.189        2
3.613        2
1.013        2
4.275        2
2.986        2
3.137        2
3.239        2
3.681        2
3.602        2
3.623        2
4.220        2
4.345        2
4.226        2
1.975        2
1.039        2
3.742        2
4.006        2
3.684        2
3.835        2
1.874        2
3.620        2
3.953        2
3.943        2
4.098        2
4.186        2
3.802        2
4.315        2
4.532        2
3.903        2
3.683        2
4.206        2
4.292        2
3.690        2
4.285        2
4.323        2
3.744        2
2.845        2
4.368        2
3.803        2
3.033        2
4.215        2
4.377        2
3.969        2
3.770        2
3.647        2
2.737        2
3.145        2
3.053        2
3.124        2
3.875        2
1.023        2
4.095        2
3.866        2
2.808        2
3.696        2
3.148        2
3.018        2
2.795        2
2.953        2
4.022        2
3.851        2
4.388        2
3.882        2
3.673        2
3.182        2
3.287        2
4.099        2
4.780        2
3.026        2
3.896        2
3.658        2
3.632        2
4.634        2
3.043        2
1.986        2
4.132        2
4.386        2
3.715        2
1.919        2
3.843        2
3.025        2
3.880        2
2.935        2
3.012        2
2.088        2
1.881        2
1.892        2
4.023        2
3.174        2
4.138        2
2.998        2
2.779        2
4.324        2
4.083        2
3.864        2
3.825        2
3.257        2
3.248        2
3.760        2
4.357        2
4.309        2
4.234        2
3.234        2
4.260        2
3.885        2
3.922        2
3.627        2
3.189        2
4.372        2
4.249        2
3.920        2
4.387        2
3.737        2
2.966        2
3.701        2
4.043        2
4.334        2
3.651        2
3.804        2
3.991        2
3.059        2
4.326        2
3.005        2
3.747        2
3.190        2
3.871        2
4.160        2
1.097        2
3.269        2
2.891        2
5.323        2
5.572        2
4.062        2
3.956        2
2.039        2
2.788        2
3.048        2
2.099        2
3.709        2
3.710        2
3.910        2
2.975        2
4.257        2
3.862        2
2.883        2
4.028        2
4.321        2
4.077        2
4.100        2
2.821        2
4.107        2
4.177        2
2.946        2
4.375        2
3.972        2
2.851        2
4.952        2
2.778        2
3.144        2
4.116        2
3.714        2
4.130        2
4.133        2
2.178        2
4.317        2
3.089        2
3.847        2
3.700        2
4.266        2
3.891        2
4.179        2
4.243        2
2.785        2
3.780        2
4.277        2
3.840        2
4.335        2
2.918        2
1.038        2
3.133        2
3.766        2
3.616        2
4.075        2
2.097        2
3.932        2
3.151        2
3.877        2
3.808        2
4.176        2
9.000        2
3.934        1
5.465        1
4.365        1
3.729        1
3.652        1
5.410        1
5.405        1
3.670        1
3.725        1
3.952        1
4.801        1
4.298        1
4.799        1
4.355        1
4.537        1
3.998        1
5.194        1
4.297        1
3.650        1
3.789        1
4.265        1
4.399        1
4.250        1
4.276        1
4.701        1
10.748       1
4.036        1
3.945        1
4.856        1
5.457        1
4.065        1
3.854        1
3.907        1
4.239        1
4.554        1
6.591        1
4.089        1
5.361        1
3.677        1
4.764        1
5.437        1
4.192        1
2.899        1
4.822        1
5.426        1
3.996        1
5.023        1
5.126        1
4.278        1
4.703        1
4.400        1
3.796        1
5.209        1
3.842        1
4.293        1
4.030        1
4.282        1
4.833        1
5.448        1
5.182        1
4.602        1
5.371        1
3.849        1
3.001        1
2.100        1
3.695        1
4.085        1
4.082        1
4.270        1
2.915        1
4.211        1
4.014        1
5.463        1
3.887        1
5.042        1
4.272        1
2.829        1
2.890        1
5.344        1
3.853        1
3.628        1
5.040        1
4.093        1
4.396        1
4.052        1
2.729        1
2.819        1
5.416        1
3.857        1
3.049        1
4.124        1
5.498        1
3.785        1
4.390        1
5.027        1
4.267        1
4.230        1
4.198        1
5.447        1
3.884        1
4.934        1
4.008        1
4.055        1
4.902        1
4.760        1
4.661        1
7.537        1
3.734        1
4.894        1
2.880        1
4.322        1
4.047        1
3.679        1
3.610        1
4.893        1
4.233        1
4.965        1
5.380        1
4.091        1
4.973        1
4.084        1
4.048        1
4.385        1
5.499        1
4.051        1
5.064        1
3.817        1
5.348        1
3.121        1
4.170        1
4.106        1
5.188        1
3.721        1
4.820        1
4.311        1
3.768        1
5.606        1
4.560        1
3.806        1
4.327        1
4.316        1
3.784        1
2.801        1
3.931        1
3.031        1
4.004        1
3.820        1
5.454        1
5.483        1
3.722        1
4.157        1
3.645        1
5.331        1
5.055        1
4.920        1
4.709        1
5.298        1
3.799        1
3.642        1
5.176        1
6.052        1
3.995        1
4.214        1
3.989        1
4.025        1
4.031        1
4.755        1
5.411        1
5.233        1
3.937        1
4.208        1
4.041        1
5.986        1
4.566        1
5.081        1
3.698        1
9.384        1
3.691        1
3.900        1
4.824        1
4.188        1
4.342        1
3.865        1
4.814        1
3.657        1
2.806        1
4.518        1
3.120        1
3.753        1
3.844        1
3.794        1
3.917        1
5.283        1
4.063        1
3.941        1
4.302        1
4.108        1
4.174        1
4.971        1
4.002        1
3.756        1
3.726        1
4.102        1
5.474        1
5.201        1
3.965        1
4.202        1
4.834        1
4.224        1
5.490        1
5.472        1
5.145        1
4.540        1
5.187        1
5.249        1
4.049        1
3.659        1
4.090        1
2.971        1
3.638        1
4.887        1
2.989        1
3.697        1
4.933        1
5.496        1
5.114        1
3.221        1
4.060        1
3.839        1
5.116        1
3.611        1
3.810        1
5.433        1
3.894        1
3.618        1
4.252        1
4.301        1
4.861        1
4.575        1
4.648        1
4.284        1
4.005        1
5.180        1
4.295        1
6.085        1
5.445        1
4.855        1
3.717        1
4.225        1
5.456        1
4.204        1
2.842        1
4.115        1
4.034        1
4.361        1
5.197        1
2.905        1
2.965        1
4.056        1
4.876        1
5.338        1
3.694        1
4.094        1
5.039        1
2.112        1
5.263        1
2.705        1
4.963        1
4.237        1
4.147        1
4.529        1
3.893        1
5.029        1
4.555        1
2.823        1
2.947        1
5.395        1
4.369        1
5.358        1
3.267        1
4.210        1
5.475        1
5.054        1
4.918        1
4.839        1
4.118        1
4.509        1
5.291        1
3.926        1
3.988        1
2.943        1
2.773        1
2.910        1
3.169        1
4.508        1
4.009        1
3.827        1
3.823        1
4.392        1
4.010        1
5.387        1
4.354        1
3.936        1
4.244        1
4.558        1
4.875        1
4.524        1
4.382        1
4.967        1
1.976        1
5.109        1
3.757        1
3.030        1
4.344        1
4.281        1
3.831        1
4.813        1
2.936        1
4.017        1
4.358        1
4.931        1
5.723        1
4.070        1
5.079        1
4.242        1
5.339        1
4.209        1
4.707        1
3.689        1
5.230        1
3.718        1
3.758        1
5.392        1
3.901        1
3.921        1
7.580        1
3.890        1
3.811        1
4.205        1
5.276        1
4.078        1
4.159        1
5.214        1
4.140        1
4.600        1
4.657        1
4.923        1
3.883        1
5.346        1
4.153        1
4.201        1
4.597        1
3.752        1
4.156        1
4.339        1
2.768        1
5.450        1
5.402        1
4.175        1
6.307        1
3.964        1
3.974        1
4.212        1
4.927        1
4.033        1
4.995        1
3.930        1
3.042        1
3.923        1
4.941        1
3.836        1
4.919        1
5.458        1
4.542        1
9.543        1
3.745        1
4.653        1
4.232        1
4.015        1
4.066        1
7.623        1
2.758        1
3.639        1
5.337        1
4.121        1
2.992        1
3.980        1
4.736        1
3.981        1
2.194        1
4.253        1
3.924        1
3.990        1
3.982        1
3.813        1
2.707        1
3.939        1
5.130        1
4.348        1
4.943        1
3.740        1
4.885        1
4.850        1
5.258        1
3.728        1
3.942        1
3.738        1
4.832        1
4.269        1
3.225        1
2.988        1
3.954        1
3.265        1
4.236        1
3.641        1
4.370        1
5.562        1
3.685        1
3.899        1
4.001        1
3.872        1
3.713        1
5.855        1
4.203        1
5.147        1
4.181        1
3.654        1
3.736        1
4.672        1
4.169        1
3.661        1
6.480        1
3.682        1
5.407        1
3.128        1
4.012        1
4.730        1
2.995        1
3.772        1
4.172        1
3.951        1
4.113        1
4.011        1
4.086        1
4.180        1
4.667        1
4.231        1
3.666        1
4.131        1
2.862        1
3.600        1
5.497        1
4.219        1
3.606        1
4.759        1
3.833        1
5.742        1
5.060        1
0.951        1
4.216        1
3.829        1
3.944        1
4.389        1
3.624        1
5.381        1
4.680        1
4.271        1
3.612        1
3.298        1
4.088        1
3.634        1
4.319        1
3.916        1
2.787        1
4.695        1
5.241        1
5.123        1
5.299        1
4.145        1
4.150        1
4.757        1
3.625        1
3.828        1
4.970        1
5.135        1
3.678        1
3.699        1
4.241        1
4.069        1
4.280        1
4.068        1
6.129        1
4.383        1
4.506        1
4.207        1
2.061        1
3.986        1
4.307        1
5.008        1
4.134        1
2.990        1
3.997        1
3.858        1
3.814        1
5.293        1
3.240        1
4.936        1
4.395        1
3.870        1
3.873        1
4.892        1
5.317        1
3.809        1
4.802        1
5.225        1
4.238        1
4.178        1
1.959        1
3.773        1
3.961        1
6.492        1
4.129        1
5.565        1
4.574        1
4.092        1
2.824        1
4.318        1
5.030        1
5.066        1
4.320        1
4.079        1
4.135        1
4.938        1
3.962        1
4.721        1
4.042        1
3.889        1
5.129        1
6.788        1
4.195        1
4.869        1
2.951        1
4.247        1
3.646        1
4.185        1
3.897        1
3.868        1
4.026        1
4.097        1
3.993        1
3.807        1
2.895        1
3.816        1
10.754       1
7.313        1
Name: count, dtype: int64
--------------------------------------------------
bathroom
1.000    4873
2.000    2742
3.000     421
4.000     121
5.000      41
1.094      36
0.986      35
1.051      35
0.939      34
1.060      34
1.079      34
1.058      33
1.059      33
0.966      32
0.935      32
1.010      32
0.981      32
1.022      32
0.991      32
0.995      31
1.037      31
0.922      31
1.044      31
0.958      30
0.933      30
1.032      30
1.004      29
0.903      29
1.098      29
1.045      29
1.053      29
1.068      29
0.999      29
0.959      29
0.901      29
1.075      29
1.076      29
0.945      29
1.074      28
0.950      28
1.018      28
1.043      28
0.974      28
0.944      27
0.930      27
1.061      27
0.942      27
1.085      27
0.980      27
1.092      27
1.049      27
0.961      27
0.976      27
1.020      27
0.962      26
1.015      26
0.924      26
1.089      26
1.041      26
0.911      26
0.994      26
0.953      26
0.919      26
0.905      26
0.955      26
1.008      26
1.029      26
0.934      26
0.947      26
0.996      25
1.066      25
0.948      25
1.091      25
0.912      25
0.998      25
1.050      25
1.021      25
0.926      25
1.026      25
0.975      25
0.973      24
1.047      24
1.093      24
1.023      24
1.080      24
1.003      24
0.907      24
1.017      24
1.038      24
1.099      24
1.070      24
1.056      24
0.967      24
1.025      24
0.906      24
1.009      24
0.931      24
1.035      24
0.964      24
1.046      24
1.078      24
1.086      23
1.069      23
1.013      23
0.972      23
0.923      23
0.984      23
0.940      23
1.002      23
0.946      23
1.097      23
0.963      23
0.978      23
1.024      23
0.929      22
0.943      22
1.065      22
0.965      22
1.087      22
1.036      22
0.949      22
0.993      22
0.985      22
1.033      22
1.030      21
0.927      21
0.990      21
0.917      21
0.983      21
0.968      21
0.916      21
1.001      21
0.957      21
0.928      21
1.012      21
0.938      21
0.997      21
1.088      21
0.925      21
0.913      20
0.970      20
1.019      20
1.014      20
1.031      20
1.071      20
1.005      20
0.936      20
1.054      20
1.081      20
1.073      20
0.960      20
1.062      20
0.954      20
0.909      19
1.007      19
1.067      19
0.900      19
0.952      19
1.072      19
1.052      19
1.063      19
0.979      19
0.989      19
1.042      19
0.982      18
1.039      18
0.932      18
0.914      18
1.077      18
1.048      18
1.090      18
1.095      18
1.083      18
1.064      18
0.921      18
0.971      18
0.918      18
1.027      17
0.987      17
0.908      17
0.941      17
0.969      17
1.040      17
1.084      16
0.951      16
0.904      16
1.057      16
1.034      16
1.028      16
0.937      16
1.096      15
0.988      15
1.006      15
0.902      15
1.055      15
0.956      15
1.082      14
0.977      14
2.051      14
0.920      14
2.125      14
2.183      14
1.995      14
0.992      14
2.088      14
1.849      13
0.910      13
1.957      13
1.943      13
2.169      13
1.973      13
1.933      12
2.043      12
2.075      12
2.173      12
2.145      12
2.115      12
1.980      12
1.801      12
1.011      12
1.986      12
1.802      11
1.861      11
1.951      11
1.962      11
2.070      11
2.002      11
1.983      11
1.016      11
2.127      11
2.082      11
2.103      11
1.870      11
1.975      11
2.155      11
1.998      10
1.901      10
1.914      10
1.907      10
2.157      10
2.008      10
1.968      10
1.965      10
2.143      10
2.038      10
2.077      10
1.915      10
2.122      10
1.823      10
1.881      10
1.868      10
1.879      10
2.129      10
2.175      10
1.885      10
1.859      10
1.889      10
1.961      10
0.915      10
1.903       9
6.000       9
1.860       9
1.905       9
1.949       9
1.920       9
1.840       9
1.865       9
1.900       9
1.936       9
1.892       9
2.181       9
1.819       9
2.091       9
2.080       9
2.049       9
1.896       9
2.072       9
2.165       9
1.844       9
1.994       9
1.852       9
2.137       9
1.843       9
1.977       9
2.171       9
1.846       9
2.140       9
2.142       9
2.113       9
2.161       9
1.864       9
1.834       9
1.805       9
1.100       9
1.992       9
1.813       9
2.139       9
2.074       8
1.818       8
1.947       8
2.066       8
1.945       8
1.929       8
1.891       8
2.154       8
2.031       8
2.135       8
2.076       8
2.054       8
1.871       8
2.105       8
1.897       8
2.124       8
1.836       8
2.014       8
2.068       8
1.875       8
1.878       8
2.177       8
2.019       8
2.022       8
2.048       8
2.111       8
2.184       8
2.093       8
1.893       8
2.192       8
1.910       8
2.001       8
2.100       8
1.988       8
2.166       8
2.034       8
2.046       8
2.098       8
1.841       8
1.987       8
1.810       8
2.193       8
1.886       8
2.097       8
2.196       8
1.950       8
2.032       8
1.908       8
1.985       8
2.029       8
1.997       8
2.156       8
1.815       8
1.921       7
1.982       7
2.109       7
1.817       7
2.164       7
2.021       7
2.004       7
1.874       7
1.984       7
1.991       7
1.906       7
1.829       7
1.873       7
2.087       7
1.926       7
1.806       7
1.918       7
2.007       7
1.931       7
2.017       7
2.035       7
1.970       7
2.050       7
2.033       7
2.052       7
2.090       7
1.820       7
1.974       7
2.106       7
1.922       7
2.024       7
2.110       7
1.960       7
2.079       7
2.078       7
2.061       7
2.144       7
2.138       7
2.040       7
1.867       7
1.953       7
2.003       7
1.902       7
1.894       7
1.972       7
1.850       7
2.084       7
2.036       7
1.971       7
1.938       7
1.940       7
2.067       7
2.005       7
1.827       7
2.015       7
2.185       7
1.913       7
2.053       7
2.095       7
2.189       7
1.999       7
1.851       7
1.927       6
1.952       6
2.168       6
2.085       6
2.042       6
2.112       6
1.863       6
2.028       6
1.993       6
1.979       6
2.141       6
2.114       6
1.812       6
2.006       6
2.170       6
2.041       6
1.830       6
1.948       6
1.944       6
2.025       6
1.966       6
2.134       6
2.148       6
1.862       6
1.912       6
1.963       6
2.195       6
2.188       6
2.086       6
2.191       6
1.990       6
2.064       6
1.821       6
1.925       6
1.939       6
2.136       6
2.149       6
2.187       6
1.942       6
2.117       6
2.162       6
1.909       6
1.837       6
2.198       6
2.083       6
1.967       6
1.930       6
1.877       6
1.978       6
1.856       6
1.954       6
2.179       6
2.178       6
2.126       6
1.832       5
1.826       5
2.116       5
2.121       5
2.146       5
2.159       5
1.923       5
1.941       5
2.047       5
2.147       5
2.039       5
2.060       5
2.128       5
1.816       5
2.094       5
1.989       5
2.099       5
2.120       5
1.883       5
1.946       5
2.071       5
1.855       5
2.107       5
2.058       5
2.167       5
1.811       5
1.959       5
1.899       5
2.018       5
2.009       5
2.118       5
2.065       5
2.153       5
1.898       5
2.123       5
2.062       5
2.023       5
1.858       5
1.854       5
2.133       5
1.934       5
2.197       5
2.089       5
1.911       5
2.151       5
1.831       5
1.904       5
1.824       5
2.081       5
1.822       5
1.955       5
1.996       4
2.108       4
2.063       4
1.917       4
2.092       4
1.857       4
2.069       4
2.104       4
2.160       4
2.132       4
1.887       4
2.174       4
1.872       4
2.013       4
2.130       4
2.044       4
1.919       4
1.935       4
1.964       4
2.797       4
1.814       4
1.845       4
1.808       4
2.073       4
2.055       4
1.976       4
1.956       4
2.172       4
2.030       4
1.916       4
1.848       4
2.150       4
2.176       4
2.194       4
1.937       4
2.180       4
2.186       4
2.016       4
2.026       4
1.890       4
2.182       4
1.838       4
3.249       3
1.932       3
1.958       3
2.056       3
1.853       3
2.059       3
1.969       3
2.131       3
1.880       3
2.944       3
1.804       3
1.928       3
1.876       3
2.119       3
2.785       3
2.102       3
2.027       3
1.888       3
1.842       3
1.809       3
3.173       3
1.882       3
1.803       3
1.884       3
3.078       3
2.163       3
2.010       3
3.201       3
3.298       3
2.199       3
2.818       3
2.711       3
4.393       3
3.026       3
2.722       3
2.907       3
1.828       3
3.074       3
2.841       3
1.895       3
3.004       2
2.045       2
1.847       2
2.784       2
3.234       2
2.827       2
3.245       2
1.839       2
2.152       2
1.833       2
3.143       2
3.079       2
3.256       2
3.204       2
3.067       2
2.920       2
1.866       2
2.851       2
3.138       2
2.706       2
2.897       2
2.838       2
3.154       2
3.039       2
3.005       2
1.869       2
3.244       2
3.278       2
2.895       2
3.162       2
2.020       2
2.703       2
3.085       2
3.262       2
3.947       2
3.166       2
5.299       2
2.756       2
2.928       2
3.252       2
2.731       2
2.906       2
2.739       2
3.012       2
3.214       2
1.825       2
3.184       2
3.215       2
3.264       2
4.309       2
2.983       2
2.707       2
2.964       2
3.002       2
2.096       2
3.149       2
1.981       2
3.259       2
2.747       2
3.192       2
2.767       2
2.868       2
2.878       2
3.086       2
2.200       2
2.190       2
3.721       2
3.093       2
3.261       2
2.986       2
3.869       2
3.095       2
3.970       2
2.720       2
3.190       2
3.076       2
2.742       2
2.995       2
3.241       2
2.876       2
2.993       2
2.057       2
2.957       2
2.101       2
2.792       2
5.093       2
2.721       2
2.751       2
2.857       2
3.161       2
2.898       2
3.101       2
3.009       2
2.910       2
8.000       2
2.866       1
3.041       1
3.187       1
4.903       1
3.061       1
3.228       1
3.232       1
2.976       1
2.959       1
2.904       1
3.703       1
3.224       1
5.908       1
3.139       1
3.081       1
2.829       1
4.679       1
3.863       1
2.824       1
4.252       1
4.914       1
4.325       1
4.255       1
3.052       1
3.275       1
4.502       1
2.914       1
3.146       1
3.054       1
3.976       1
3.855       1
4.208       1
3.040       1
4.374       1
2.913       1
2.886       1
2.991       1
4.841       1
3.027       1
4.746       1
3.010       1
2.852       1
4.900       1
2.912       1
4.295       1
3.025       1
3.627       1
3.297       1
3.719       1
3.294       1
3.219       1
4.158       1
3.021       1
2.885       1
2.916       1
3.803       1
3.251       1
4.233       1
2.884       1
2.863       1
1.924       1
3.051       1
2.814       1
3.769       1
3.231       1
4.203       1
2.940       1
3.140       1
1.807       1
3.107       1
5.857       1
4.745       1
4.370       1
4.132       1
4.340       1
5.717       1
3.885       1
5.393       1
3.178       1
3.175       1
4.929       1
2.861       1
4.855       1
3.072       1
3.152       1
4.119       1
4.854       1
3.705       1
2.773       1
2.977       1
3.133       1
3.290       1
2.799       1
3.640       1
3.601       1
2.781       1
4.326       1
3.287       1
2.816       1
3.058       1
2.771       1
2.975       1
3.242       1
5.490       1
3.642       1
4.112       1
4.353       1
2.011       1
5.384       1
5.263       1
2.758       1
2.809       1
3.267       1
2.905       1
3.008       1
3.937       1
3.070       1
2.709       1
3.125       1
2.888       1
4.689       1
3.695       1
2.037       1
3.254       1
3.213       1
3.129       1
3.263       1
4.701       1
2.718       1
3.221       1
4.044       1
3.293       1
1.800       1
2.911       1
3.189       1
4.285       1
2.821       1
2.736       1
4.139       1
5.251       1
2.840       1
5.759       1
4.754       1
2.755       1
3.230       1
3.206       1
2.754       1
3.202       1
2.871       1
3.239       1
2.778       1
4.140       1
3.177       1
4.198       1
4.055       1
2.733       1
3.113       1
3.073       1
5.366       1
4.323       1
3.952       1
2.936       1
3.094       1
5.474       1
3.104       1
5.063       1
3.159       1
4.668       1
2.958       1
2.880       1
2.930       1
2.815       1
3.281       1
3.216       1
4.789       1
2.903       1
2.808       1
3.276       1
2.925       1
2.812       1
2.853       1
4.028       1
4.266       1
3.015       1
3.277       1
3.218       1
3.034       1
5.431       1
2.973       1
3.176       1
2.856       1
3.050       1
2.788       1
2.947       1
3.222       1
2.854       1
4.659       1
3.257       1
4.964       1
5.322       1
2.990       1
3.077       1
3.273       1
3.265       1
3.236       1
3.200       1
3.111       1
4.343       1
4.279       1
2.867       1
4.025       1
4.826       1
3.209       1
2.732       1
3.698       1
5.195       1
4.333       1
3.155       1
4.050       1
4.011       1
4.695       1
4.116       1
3.128       1
4.312       1
3.291       1
3.959       1
2.847       1
3.296       1
2.830       1
5.218       1
2.719       1
4.141       1
3.185       1
2.780       1
2.762       1
3.150       1
3.199       1
2.819       1
2.804       1
2.921       1
2.887       1
4.899       1
2.803       1
3.836       1
2.761       1
3.829       1
7.160       1
2.994       1
4.773       1
3.614       1
3.007       1
5.444       1
3.762       1
3.188       1
3.044       1
3.602       1
4.377       1
3.725       1
4.371       1
3.655       1
2.806       1
4.335       1
3.279       1
3.123       1
2.848       1
3.103       1
2.926       1
1.835       1
3.283       1
2.765       1
4.948       1
2.890       1
4.297       1
4.113       1
2.813       1
2.823       1
3.271       1
4.797       1
3.047       1
2.894       1
2.774       1
3.135       1
4.400       1
2.850       1
2.702       1
3.068       1
2.846       1
3.205       1
2.929       1
7.000       1
2.862       1
5.898       1
3.046       1
2.946       1
2.787       1
2.704       1
3.087       1
3.300       1
3.119       1
4.690       1
2.701       1
2.791       1
4.105       1
3.953       1
4.196       1
3.182       1
3.780       1
2.012       1
3.255       1
3.083       1
3.975       1
4.204       1
2.158       1
2.724       1
3.246       1
2.826       1
2.743       1
4.321       1
4.064       1
3.053       1
2.828       1
Name: count, dtype: int64

room_counts_list = []
# Iterate through each integer value of rooms
for i in range(1, 1 + int(max(df['rooms']))):
    count = df['rooms'][df['rooms'] == i].count()  # Count occurrences for the current value
    room_counts_list.append({'rooms': i, 'count': count})  # Add result to the list

# Convert the list of dictionaries into a DataFrame
room_counts = pd.DataFrame(room_counts_list)

#calculate totals
int_rooms=room_counts['count'].sum()

room_counts['int_prop']=room_counts['count']/int_rooms
room_counts['net_prop']=room_counts['count']/16376
room_counts

print(f'The total number of observations with an integer number for variable "rooms" is {room_counts['count'].sum()}, this represents {room_counts['net_prop'].sum()*100:.2f}% of total observations')

The total number of observations with an integer number for variable "rooms" is 8000, this represents 48.85% of total observations

bathroom_counts_list = []
# Iterate through each integer value of rooms
for i in range(1, 1 + int(max(df['bathroom']))):
    count = df['bathroom'][df['bathroom'] == i].count()  # Count occurrences for the current value
    bathroom_counts_list.append({'bathroom': i, 'count': count})  # Add result to the list

# Convert the list of dictionaries into a DataFrame
bathroom_counts = pd.DataFrame(bathroom_counts_list)

#calculate totals
int_bathroom=bathroom_counts['count'].sum()

bathroom_counts['int_prop']=bathroom_counts['count']/int_rooms
bathroom_counts['net_prop']=bathroom_counts['count']/16376
bathroom_counts

print(f'The total number of observations with an integer number for variable "bathroom" is {bathroom_counts['count'].sum()}, this represents {bathroom_counts['net_prop'].sum()*100:.2f}% of total observations')

The total number of observations with an integer number for variable "bathroom" is 8210, this represents 50.13% of total observations

# Duplicates
print(df.duplicated().sum()) # Checking for duplicate entries in the data

0

df2=df.copy()

null_counts = df2.isnull().sum()
null_percentage = (null_counts / len(df2)) * 100
null_summary = pd.DataFrame({'Null Count': null_counts,'Null Percentage': null_percentage.round(2)})
null_summary

# Create a new dataframe with rows that contain at least one missing value
df_missing = df[df.isnull().any(axis=1)]

# Reset index for better readability (optional)
df_missing = df_missing.reset_index(drop=True)

df_missing.shape

(2311, 10)

df_missing.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2311 entries, 0 to 2310
Data columns (total 10 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   Unnamed: 0           2311 non-null   int64  
 1   price                2311 non-null   int64  
 2   rooms                1901 non-null   float64
 3   bathroom             1924 non-null   float64
 4   lift                 2311 non-null   bool   
 5   terrace              2311 non-null   bool   
 6   square_meters        1903 non-null   float64
 7   real_state           1393 non-null   object 
 8   neighborhood         2311 non-null   object 
 9   square_meters_price  1872 non-null   float64
dtypes: bool(2), float64(4), int64(2), object(2)
memory usage: 149.1+ KB

mask1 = df2["square_meters"].isna() & df2["price"].notna() & df2["square_meters_price"].notna()
df2.loc[mask1, "square_meters"] = df2["price"] / df2["square_meters_price"]
df2.isnull().sum() # Checking for missing values in the data

Unnamed: 0               0
price                    0
rooms                  410
bathroom               387
lift                     0
terrace                  0
square_meters           19
real_state             918
neighborhood             0
square_meters_price    439
dtype: int64

mask2 = df2["square_meters"].notna() & df2["price"].notna() & df2["square_meters_price"].isna()
df2.loc[mask2, "square_meters_price"] = df2["price"] / df2["square_meters"]
df2.isnull().sum() # Checking for missing values in the data

Unnamed: 0               0
price                    0
rooms                  410
bathroom               387
lift                     0
terrace                  0
square_meters           19
real_state             918
neighborhood             0
square_meters_price     19
dtype: int64

df2[(df2['square_meters_price'].isnull())&(df2['square_meters'].isnull())]

df2['square_meters_price'] = df2['square_meters_price'].fillna(df2.groupby(['real_state', 'neighborhood'])['square_meters_price'].transform('mean'))
df2.isnull().sum() # Checking for missing values in the data

Unnamed: 0               0
price                    0
rooms                  410
bathroom               387
lift                     0
terrace                  0
square_meters           19
real_state             918
neighborhood             0
square_meters_price      0
dtype: int64

df2.loc[df2['square_meters'].isna(), 'square_meters'] = df2['price'] / df2['square_meters_price']
df2.isnull().sum() # Checking for missing values in the data

Unnamed: 0               0
price                    0
rooms                  410
bathroom               387
lift                     0
terrace                  0
square_meters            0
real_state             918
neighborhood             0
square_meters_price      0
dtype: int64

# Compute the most common (mode) real_state for each neighborhood
mode_real_state = df2.groupby("neighborhood")["real_state"].apply(lambda x: x.mode()[0] if not x.mode().empty else np.nan)

# Fill missing values in real_state based on the mode of each neighborhood
df2["real_state"] = df2["real_state"].fillna(df2["neighborhood"].map(mode_real_state))

df2.isnull().sum() # Checking for missing values in the data

Unnamed: 0               0
price                    0
rooms                  410
bathroom               387
lift                     0
terrace                  0
square_meters            0
real_state               0
neighborhood             0
square_meters_price      0
dtype: int64

#df2['rooms'] = df2['rooms'].fillna(df2.groupby(['real_state', 'neighborhood'])['rooms'].transform('mean'))
df2['rooms'] = df2['rooms'].fillna(df2.groupby(['real_state', 'neighborhood'])['rooms'].transform('median'))
df2.isnull().sum() # Checking for missing values in the data

Unnamed: 0               0
price                    0
rooms                    0
bathroom               387
lift                     0
terrace                  0
square_meters            0
real_state               0
neighborhood             0
square_meters_price      0
dtype: int64

#df2['bathroom'] = df2['bathroom'].fillna(df2.groupby(['real_state', 'neighborhood'])['bathroom'].transform('mean'))
df2['bathroom'] = df2['bathroom'].fillna(df2.groupby(['real_state', 'neighborhood'])['bathroom'].transform('median'))
df2.isnull().sum() # Checking for missing values in the data

Unnamed: 0             0
price                  0
rooms                  0
bathroom               0
lift                   0
terrace                0
square_meters          0
real_state             0
neighborhood           0
square_meters_price    0
dtype: int64

df3=df2.copy()

df3=df3.drop(['Unnamed: 0'],axis=1)
df3.head()

df3.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 16376 entries, 0 to 16375
Data columns (total 9 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   price                16376 non-null  int64  
 1   rooms                16376 non-null  float64
 2   bathroom             16376 non-null  float64
 3   lift                 16376 non-null  bool   
 4   terrace              16376 non-null  bool   
 5   square_meters        16376 non-null  float64
 6   real_state           16376 non-null  object 
 7   neighborhood         16376 non-null  object 
 8   square_meters_price  16376 non-null  float64
dtypes: bool(2), float64(4), int64(1), object(2)
memory usage: 927.7+ KB

# Select rows where 'rooms' or 'bathroom' contain float values
df3_float = df3[df3[["rooms", "bathroom"]].select_dtypes(include=["float64"]).notna().any(axis=1)]

df3_float.shape

(16376, 9)

df3['rooms'] = df3['rooms'].apply(lambda x: 1 if x < 1 else round(x)).astype(int)
df3.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 16376 entries, 0 to 16375
Data columns (total 9 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   price                16376 non-null  int64  
 1   rooms                16376 non-null  int64  
 2   bathroom             16376 non-null  float64
 3   lift                 16376 non-null  bool   
 4   terrace              16376 non-null  bool   
 5   square_meters        16376 non-null  float64
 6   real_state           16376 non-null  object 
 7   neighborhood         16376 non-null  object 
 8   square_meters_price  16376 non-null  float64
dtypes: bool(2), float64(3), int64(2), object(2)
memory usage: 927.7+ KB

df3['bathroom'] = df3['bathroom'].apply(lambda x: 1 if x < 1 else round(x)).astype(int)
df3.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 16376 entries, 0 to 16375
Data columns (total 9 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   price                16376 non-null  int64  
 1   rooms                16376 non-null  int64  
 2   bathroom             16376 non-null  int64  
 3   lift                 16376 non-null  bool   
 4   terrace              16376 non-null  bool   
 5   square_meters        16376 non-null  float64
 6   real_state           16376 non-null  object 
 7   neighborhood         16376 non-null  object 
 8   square_meters_price  16376 non-null  float64
dtypes: bool(2), float64(2), int64(3), object(2)
memory usage: 927.7+ KB

df3.describe(include="all").T # statistical summary of the data.

# function to check for outliers
def count_outliers(df):
    outlier_count=0
    for column in df.select_dtypes(include=np.number).columns:
        outliers=len(df[(df[column] < df[column].quantile(0.25)-1.5*(df[column].quantile(0.75)-df[column].quantile(0.25))) | (df[column] > df[column].quantile(0.75)+1.5*(df[column].quantile(0.75)-df[column].quantile(0.25)))][column])
        print(f'{column}: {outliers} outliers ({outliers/df.shape[0]*100:.2f}%)')
        outlier_count+= outliers
    return outlier_count

df4=df3.copy()

count_outliers(df)

Unnamed: 0: 0 outliers (0.00%)
price: 1778 outliers (10.86%)
rooms: 870 outliers (5.31%)
bathroom: 308 outliers (1.88%)
square_meters: 1177 outliers (7.19%)
square_meters_price: 1165 outliers (7.11%)

5298

df.shape

(16376, 10)

count_outliers(df4)

price: 1778 outliers (10.86%)
rooms: 505 outliers (3.08%)
bathroom: 308 outliers (1.88%)
square_meters: 1206 outliers (7.36%)
square_meters_price: 1201 outliers (7.33%)

4998

df4.shape

(16376, 9)

# Z-Score Method
df5=df4[(np.abs(df4.select_dtypes(include=np.number).apply(zscore))<2).all(axis=1)] #drop over 2 standard deviations
count_outliers(df5)

price: 960 outliers (6.73%)
rooms: 0 outliers (0.00%)
bathroom: 0 outliers (0.00%)
square_meters: 499 outliers (3.50%)
square_meters_price: 593 outliers (4.16%)

2052

df5.shape

(14269, 9)

df6=df5.copy()
for column in df6.select_dtypes(include=np.number).columns:
    df6[column]=np.clip(df6[column], df6[column].quantile(0.25)-1.5*(df6[column].quantile(0.75)-df6[column].quantile(0.25)), df6[column].quantile(0.75)+1.5*(df6[column].quantile(0.75)-df6[column].quantile(0.25)))
df6.shape

(14269, 9)

count_outliers(df6)

price: 0 outliers (0.00%)
rooms: 0 outliers (0.00%)
bathroom: 0 outliers (0.00%)
square_meters: 0 outliers (0.00%)
square_meters_price: 0 outliers (0.00%)

0

df6.info()

<class 'pandas.core.frame.DataFrame'>
Index: 14269 entries, 0 to 16375
Data columns (total 9 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   price                14269 non-null  int64  
 1   rooms                14269 non-null  int64  
 2   bathroom             14269 non-null  int64  
 3   lift                 14269 non-null  bool   
 4   terrace              14269 non-null  bool   
 5   square_meters        14269 non-null  float64
 6   real_state           14269 non-null  object 
 7   neighborhood         14269 non-null  object 
 8   square_meters_price  14269 non-null  float64
dtypes: bool(2), float64(2), int64(3), object(2)
memory usage: 919.7+ KB

df6.describe(include="all").T # statistical summary of the data.

df.to_csv('df_ORIGINAL_DATA.csv', index=False)  # Save a copy of original data

df_missing.to_csv('df_MISSING_DATA.csv', index=False)  # Save a copy of missing data to be imputed

df2.to_csv('df2_IMPUTED_DATA.csv', index=False)  # Save a copy of data after imputitation of missing values

df3_float.to_csv('df3_WRONG FEATURES_DATA.csv', index=False)  # Save a copy of data before feature engineering

df3.to_csv('df3_FATURE ENGINEERED_DATA.csv', index=False)  # Save a copy of data after feature engineering

df6.to_csv('df6_WITHOUT OUTLIERS_DATA.csv', index=False)  # Save a copy of data after outliers handling

def univariate_numerical(data):
    '''
    Function to generate two plots for each numerical variable
    Histplot for variable distribution
    Boxplot for statistical summary 
    '''
    # Select numerical columns
    numerical_cols = data.select_dtypes(include=[np.number]).columns
    
    # Determine the number of rows and columns
    num_vars = len(numerical_cols)
    num_cols = 4
    num_rows = int(np.ceil(num_vars * 2 / num_cols))
    
    # Create a figure with the specified size
    fig, axes = plt.subplots(num_rows, num_cols, figsize=(5*num_cols, num_rows * 5))
    
    # Flatten the axes array for easy iteration
    axes = axes.flatten()
    
    # Plot each variable with a histplot and a boxplot
    for i, col in enumerate(numerical_cols):
        mean_value = data[col].mean()
        
        # Histplot with KDE
        sns.histplot(data[col], kde=True, ax=axes[i*2])
        axes[i*2].axvline(mean_value, color='r', linestyle='--')
        axes[i*2].set_title(f'Distribution of {col}')
        axes[i*2].text(mean_value, axes[i*2].get_ylim()[1]*0.8, f'Mean: {mean_value:.2f}', color='r', va='baseline', ha='left',rotation=90)
        
        # Boxplot
        sns.boxplot(y=data[col], ax=axes[i*2 + 1])
        axes[i*2 + 1].axhline(mean_value, color='r', linestyle='--')
        axes[i*2 + 1].set_title(f'Boxplot of {col}')
        axes[i*2 + 1].text(axes[i*2 + 1].get_xlim()[1]*0.8, mean_value, f'mean: {mean_value:.2f}', color='r', va='baseline', ha='right')
    
    # Hide any remaining empty subplots
    for j in range(num_vars * 2, len(axes)):
        fig.delaxes(axes[j])
    
    # Adjust layout
    plt.tight_layout()
    plt.show()

def univariate_categorical(data):
    '''
    Function to generate countplot for each categorical variable
    Labeled with count and percentage
    '''
    # List of categorical columns
    categorical_columns = data.select_dtypes(include=['object', 'category']).columns.tolist()
    
    # Number of columns in the grid
    num_cols = 4
    
    # Calculate the number of rows needed
    num_rows = (len(categorical_columns) + num_cols - 1) // num_cols
    
    # Create the grid
    fig, axes = plt.subplots(num_rows, num_cols, figsize=(5*num_cols, num_rows * 5), constrained_layout=True)
    axes = axes.flatten()
    
    # Plot each countplot in the grid
    for i, col in enumerate(categorical_columns):
        ax = axes[i]
        plot = sns.countplot(x=col, data=data, order=data[col].value_counts().index, ax=ax)
        ax.set_title(f'Count of {col}')
           
        # Add total count and percentage annotations
        total = len(data)
        for p in plot.patches:
            height = p.get_height()
            percentage = f'{(height / total * 100):.1f}%'
            plot.text(x=p.get_x() + p.get_width() / 2,
                      y=height + 2,
                      s=f'{height:.0f}\n({percentage})',
                      ha='center')
        
        # Limit x-axis labels to avoid overlap
        ax.set_xticklabels(ax.get_xticklabels(), rotation=45, ha='right')
    
    # Remove any empty subplots
    for j in range(i + 1, len(axes)):
        fig.delaxes(axes[j])
    
    # Show the plot
    plt.show()

# Function to plot crosstab with labels
def plot_crosstab_bar_count(df, var_interest):
    '''
    Function to create a barplot of crosstab of the variable of interest vs each of the rest of categorical variables
    Labeled with counts
    '''
    # Extract categorical columns excluding the variable of interest
    cat_cols = df.select_dtypes(include=['category', 'object','bool']).columns.tolist()
    cat_cols.remove(var_interest)
    
    # Determine the grid size
    num_vars = len(cat_cols)
    num_cols = 3  # Number of columns in the grid
    num_rows = (num_vars // num_cols) + int(num_vars % num_cols > 0)

    # Create a grid of subplots
    fig, axes = plt.subplots(num_rows, num_cols, figsize=(5*num_cols, num_rows * 5), constrained_layout=True)
    axes = axes.flatten()  # Flatten the axes array for easy iteration

    for i, col in enumerate(cat_cols):
        # Create a crosstab
        crosstab = pd.crosstab(df[col], df[var_interest])
        
        # Plot the crosstab as a bar plot
        crosstab.plot(kind='bar', stacked=True, ax=axes[i])
        
        # Annotate counts in the middle of each bar section
        for bar in axes[i].patches:
            height = bar.get_height()
            if height > 0:
                axes[i].annotate(f'{int(height)}', 
                                 (bar.get_x() + bar.get_width() / 2, bar.get_y() + height / 2),
                                 ha='center', va='center', fontsize=10, color='black')
        
        # Add total labels at the top of each bar
        totals = crosstab.sum(axis=1)
        for j, total in enumerate(totals):
            axes[i].annotate(f'Total: {total}', 
                             (j, totals[j]), 
                             ha='center', va='bottom', weight='bold')

    # Hide any remaining empty subplots
    for j in range(i + 1, len(axes)):
        fig.delaxes(axes[j])

    plt.tight_layout()
    plt.show()

# Usage
#plot_crosstab_bar_count(df, var_interest='var_interest')

def plot_crosstab_heat_perc(df, var_interest,df_name="DataFrame"):
    '''
    Function to create a heatmap of crosstab of the variable of interest vs each of the rest of catagorical variables
    Labeled with counts, percentage by row, percentage by column
    '''
    # Extract categorical columns excluding the variable of interest
    cat_cols = df.select_dtypes(include=['category', 'object']).columns.tolist()
    cat_cols.remove(var_interest)
    
    # Determine the grid size
    num_vars = len(cat_cols)
    num_cols = 3  # Number of columns in the grid
    num_rows = (num_vars // num_cols) + int(num_vars % num_cols > 0)

    # Create a grid of subplots
    fig, axes = plt.subplots(num_rows, num_cols, figsize=(6*num_cols, num_rows * 6))
    axes = axes.flatten()  # Flatten the axes array for easy iteration

    for i, col in enumerate(cat_cols):
        # Create crosstabs
        crosstab = pd.crosstab(df[col], df[var_interest])
        crosstab_perc_row = crosstab.div(crosstab.sum(axis=1), axis=0) * 100
        crosstab_perc_col = crosstab.div(crosstab.sum(axis=0), axis=1) * 100

        # Combine counts with percentages
        crosstab_combined = crosstab.astype(str) + "\n" + \
                            crosstab_perc_row.round(2).astype(str) + "%" + "\n" + \
                            crosstab_perc_col.round(2).astype(str) + "%"

        # Plot the crosstab as a heatmap
        sns.heatmap(crosstab, annot=crosstab_combined, fmt='', cmap='Blues', ax=axes[i], cbar=False, annot_kws={"size": 8})
        axes[i].set_title(f'Crosstab of {col} and {var_interest} - {df_name}', fontsize=12)

    # Hide any remaining empty subplots
    for j in range(i + 1, len(axes)):
        fig.delaxes(axes[j])

    # Adjust layout to prevent label overlapping
    plt.subplots_adjust(hspace=0.4, wspace=0.4)  # Add more space between subplots
    plt.tight_layout()
    plt.show()
    
# Usage
#plot_crosstab_heat_perc(df, var_interest='var_interest')

def boxplot_by_group(df, group, var, outliers, df_name="DataFrame"):
    '''
    boxplot for a numerical variable of interest vs a categorical variable
    with or without outliers
    includes data mean and mean by category
    '''
    # Calculate the average for the variable
    var_avg = df[var].mean()
    
    # Calculate variable mean per group
    var_means = df.groupby(group)[var].mean()
    
    # Sort by means and get the sorted order
    var_sorted = var_means.sort_values(ascending=False).index
    
    # Reorder the DataFrame by the sorted group
    df[group] = pd.Categorical(df[group], categories=var_sorted, ordered=True)
    
    # Create the boxplot with the reordered sectors
    ax = sns.boxplot(data=df, x=group, y=var, order=var_sorted, showfliers=outliers)
    
    # Add horizontal line for average variable value
    plt.axhline(var_avg, color='red', linestyle='--', label=f'Avg {var}: {var_avg:.2f}')
    
    # Scatter plot for means
    x_positions = range(len(var_means.sort_values(ascending=False)))
    plt.scatter(x=x_positions, y=var_means.sort_values(ascending=False), color='red', label='Mean', zorder=5)
    
    # Add labels to each red dot with the mean value
    for i, mean in enumerate(var_means.sort_values(ascending=False)):
        plt.text(i, mean, f'{mean:.2f}', color='red', ha='center', va='bottom')
    
    # Rotate x-axis labels
    plt.xticks(ticks=x_positions, labels=var_means.sort_values(ascending=False).index, rotation=90)
    
    # Add a legend
    plt.legend()
    plt.xlabel('')  # Remove x-axis title
    
    # Add plot title with DataFrame name
    plt.title(f'Boxplot of {var} by {group} - {df_name}')
    
    # Adjust layout
    plt.tight_layout()
    
    # Display the plot
    #plt.show()

    # Get the top 3 categories
    top_3_categories = var_means.sort_values(ascending=False).head(3).index.tolist()
    top_3=",".join(top_3_categories)
    # Print the top 3 categories
    print(f'Top 3 {group} by {var} mean value are: {top_3}')

# Define the function to create and display side-by-side boxplots
def side_by_side_boxplot(df1, df2, group, var, outliers, title1, title2):
    fig, axes = plt.subplots(1, 2, figsize=(18, 6), sharey=True)
    
    # First subplot for df1
    plt.sca(axes[0])
    boxplot_by_group(df1, group, var, outliers, title1)
    
    # Second subplot for df2
    plt.sca(axes[1])
    boxplot_by_group(df2, group, var, outliers, title2)
    
    # Show both plots after setup
    plt.show()

# Usage
#side_by_side_boxplot(df, df_pop, 'neighborhood', 'price', True, "All units (show outliers)", "Popular units (show outliers)")

univariate_numerical(df)

univariate_numerical(df6)

univariate_categorical(df6)

df6.loc[(df6['real_state']=="flat")].describe().T

df.loc[(df['real_state']=="flat")].describe().T

df6.loc[(df6['neighborhood']=="Eixample")].describe().T

# Create a PairGrid
g = sns.PairGrid(df6, corner=True)

# Map different plots to the grid
g.map_lower(sns.scatterplot)
g.map_diag(sns.histplot,kde=True)

# Show the plot
plt.show()

# Calculate correlation matrix
corr_matrix = df6.select_dtypes(include=np.number).corr()

# Plot correlation matrix as heatmap
plt.figure(figsize=(10, 8))
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', vmin=-1, vmax=1)
plt.title('Correlation Matrix Heatmap')
plt.show()

# Display the sorted correlation table
corr_unstacked = corr_matrix.unstack() # Unstack the correlation matrix
corr_unstacked = corr_unstacked.reset_index() # Reset the index to get 'variable1' and 'variable2' as columns
corr_unstacked.columns = ['variable1', 'variable2', 'correlation']# Rename the columns for better understanding
corr_unstacked = corr_unstacked[corr_unstacked['variable1'] != corr_unstacked['variable2']] # Remove self-correlations by filtering out rows where variable1 == variable2
corr_unstacked = corr_unstacked.drop_duplicates(subset=['correlation']) # Drop duplicates to keep only one entry per variable pair
sorted_corr = corr_unstacked.sort_values(by='correlation', key=abs, ascending=False) # Sort the DataFrame by the absolute value of correlation
#sorted_corr # Display the sorted correlation table

# Define a function to categorize the correlation level
def categorize_correlation(correlation):
    abs_corr = abs(correlation) * 100  # Convert to percentage for easier comparison
    if abs_corr < 30:
        return 'Negligible'
    elif 30 <= abs_corr < 50:
        return 'Low'
    elif 50 <= abs_corr < 70:
        return 'Moderate'
    elif 70 <= abs_corr < 90:
        return 'High'
    else:
        return 'Very High'

# Apply the function to create the corr_lvl column
sorted_corr['corr_lvl'] = sorted_corr['correlation'].apply(categorize_correlation)
sorted_corr['corr_lvl'].value_counts()

corr_lvl
Low           5
Moderate      4
Negligible    1
Name: count, dtype: int64

sorted_corr

boxplot_by_group(df6, 'neighborhood', 'price', False, df_name="(prepared data)")

Top 3 neighborhood by price mean value are: Sarria-Sant Gervasi,Eixample,Les Corts

boxplot_by_group(df6, 'neighborhood', 'square_meters', False, df_name="(prepared data)")

Top 3 neighborhood by square_meters mean value are: Eixample,Sarria-Sant Gervasi,Les Corts

boxplot_by_group(df6, 'neighborhood', 'square_meters_price', False, df_name="(prepared data)")

Top 3 neighborhood by square_meters_price mean value are: Ciutat Vella,Sarria-Sant Gervasi,Eixample

boxplot_by_group(df6, 'real_state', 'price', False, df_name="(prepared data)")

Top 3 real_state by price mean value are: apartment,attic,flat

boxplot_by_group(df6, 'real_state', 'square_meters', False, df_name="(prepared data)")

Top 3 real_state by square_meters mean value are: flat,attic,apartment

boxplot_by_group(df6, 'real_state', 'square_meters_price', False, df_name="(prepared data)")

Top 3 real_state by square_meters_price mean value are: apartment,study,attic

plot_crosstab_heat_perc(df6, var_interest='real_state',df_name="prepared data")

plot_crosstab_bar_count(df6, var_interest='lift')

plot_crosstab_bar_count(df6, var_interest='terrace')

# Define a function to evaluate and return the model's metrics
def evaluate_model(model, x_test, y_test):
    y_pred = model.predict(x_test)
    metrics = {
        "MAE": mean_absolute_error(y_test, y_pred),
        "MSE": mean_squared_error(y_test, y_pred),
        "RMSE": np.sqrt(mean_squared_error(y_test, y_pred)),
        "R2 Score": r2_score(y_test, y_pred)
    }
    return metrics

def evaluate_models_with_cv(models, X_train, y_train, X_test, y_test):
    """
    Evaluates multiple regression models using cross-validation and final test set performance.
    
    Parameters:
    models: list of tuples (model_name, model_instance)
    X_train, y_train: training data
    X_test, y_test: test data

    Returns:
    - results_df: DataFrame containing CV and test metrics for each model
    - trained_models: Dictionary of trained models for future use
    """

    results_list = []  # List to store model results
    trained_models = {}  # Dictionary to store trained models
    
    # Define 5-fold cross-validation
    kfold = KFold(n_splits=5, shuffle=True, random_state=1)

    for name, model in models:
        # Perform cross-validation on training set
        cv_results = cross_validate(
            model, X_train, y_train, 
            scoring=["neg_mean_absolute_error", "neg_mean_squared_error", "r2"],
            cv=kfold, return_train_score=False
        )

        # Extract mean values and convert negatives to positives
        train_mae = -cv_results["test_neg_mean_absolute_error"].mean()
        train_mse = -cv_results["test_neg_mean_squared_error"].mean()
        train_rmse = np.sqrt(train_mse)
        train_r2 = cv_results["test_r2"].mean()

        # Append CV results to list
        results_list.append({
            "Model": f"{name}_CV",
            "MAE": train_mae,
            "MSE": train_mse,
            "RMSE": train_rmse,
            "R2 Score": train_r2
        })

        # Train model on full training data and evaluate on test set
        model.fit(X_train, y_train)
        trained_models[name] = model  # Store trained model

        y_pred = model.predict(X_test)
        test_mae = mean_absolute_error(y_test, y_pred)
        test_mse = mean_squared_error(y_test, y_pred)
        test_rmse = np.sqrt(test_mse)
        test_r2 = r2_score(y_test, y_pred)

        # Append test set results to list
        results_list.append({
            "Model": f"{name}_Test",
            "MAE": test_mae,
            "MSE": test_mse,
            "RMSE": test_rmse,
            "R2 Score": test_r2
        })

    # Convert results list to DataFrame
    results_cv = pd.DataFrame(results_list)
    
    return results_cv, trained_models

def univariate_numerical_y(y):
    """
    Function to generate two plots for the numerical variable y:
    - Histogram for variable distribution
    - Boxplot for statistical summary
    """
    # Create a figure with two subplots
    fig, axes = plt.subplots(1, 2, figsize=(12, 5))

    # Histogram
    axes[0].hist(y, bins=30, color='blue', alpha=0.7)
    axes[0].set_title('Histogram of y')
    axes[0].set_xlabel('Value')
    axes[0].set_ylabel('Frequency')

    # Boxplot
    axes[1].boxplot(y, vert=False)
    axes[1].set_title('Boxplot of y')
    axes[1].set_xlabel('Value')

    plt.tight_layout()
    plt.show()

data=df6.copy()

# 1. Specify independent (X) and dependent (y) variables
X = data.drop(["price"], axis=1)
y = data["price"]

# 2. Create dummy variables for categorical features
X = pd.get_dummies(X, columns=['real_state', 'neighborhood'], drop_first=True)  # drop_first=True to avoid multicollinearity

# 3. Convert boolean columns to numeric (0 and 1)
bool_cols = X.select_dtypes(['bool'])
for col in bool_cols.columns:
    X[col] = X[col].astype('int')

# 4. Split data into training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=1)

# 5. Transform and scale right-skewed variables (applied **only to training data to avoid data leakage**)
pt = PowerTransformer(method='yeo-johnson')  # Works with zero/negative values

# Fit only on training data, then transform both training and test data
X_train[['square_meters', 'square_meters_price']] = pt.fit_transform(X_train[['square_meters', 'square_meters_price']])
X_test[['square_meters', 'square_meters_price']] = pt.transform(X_test[['square_meters', 'square_meters_price']])  # Transform only

# 6. Standardize the transformed numerical features (again, to prevent data leakage)
scaler = StandardScaler()
X_train[['square_meters', 'square_meters_price']] = scaler.fit_transform(X_train[['square_meters', 'square_meters_price']])
X_test[['square_meters', 'square_meters_price']] = scaler.transform(X_test[['square_meters', 'square_meters_price']])  # Use the same scaler

# 7. Add a constant to independent variables (after scaling, only for models that need it)
X_train = sm.add_constant(X_train)
X_test = sm.add_constant(X_test)

# Checking training and test sets.
print("Shape of Training set : ", X_train.shape)
print("Shape of test set : ", X_test.shape)

Shape of Training set :  (9988, 19)
Shape of test set :  (4281, 19)

X_train.head()

X_train.info()

<class 'pandas.core.frame.DataFrame'>
Index: 9988 entries, 16047 to 15324
Data columns (total 19 columns):
 #   Column                        Non-Null Count  Dtype  
---  ------                        --------------  -----  
 0   const                         9988 non-null   float64
 1   rooms                         9988 non-null   int64  
 2   bathroom                      9988 non-null   int64  
 3   lift                          9988 non-null   int64  
 4   terrace                       9988 non-null   int64  
 5   square_meters                 9988 non-null   float64
 6   square_meters_price           9988 non-null   float64
 7   real_state_attic              9988 non-null   int64  
 8   real_state_flat               9988 non-null   int64  
 9   real_state_study              9988 non-null   int64  
 10  neighborhood_Eixample         9988 non-null   int64  
 11  neighborhood_Les Corts        9988 non-null   int64  
 12  neighborhood_Sant Martí       9988 non-null   int64  
 13  neighborhood_Ciutat Vella     9988 non-null   int64  
 14  neighborhood_Gràcia           9988 non-null   int64  
 15  neighborhood_Sants-Montjuïc   9988 non-null   int64  
 16  neighborhood_Sant Andreu      9988 non-null   int64  
 17  neighborhood_Horta- Guinardo  9988 non-null   int64  
 18  neighborhood_Nou Barris       9988 non-null   int64  
dtypes: float64(3), int64(16)
memory usage: 1.5 MB

univariate_numerical(X_train)

univariate_numerical_y(y_train)

# Define a dictionary of regression models
regression_models = {
    "Linear Regression": LinearRegression(),
    "Lasso Regression": Lasso(),
    "Ridge Regression": Ridge(),
    "Decision Tree": DecisionTreeRegressor(),
    "Random Forest": RandomForestRegressor(),
    "K-Nearest Neighbors": KNeighborsRegressor(),
    "Support Vector Regressor": SVR()
}

# Initialize an empty DataFrame to store results
results_df = pd.DataFrame(columns=["Model", "MAE", "MSE", "RMSE", "R2 Score"])

%%time
# Loop through each model, train it, evaluate it, and store results
for model_name, model in regression_models.items():
    model.fit(X_train, y_train)
    metrics = evaluate_model(model, X_test, y_test)
    metrics["Model"] = model_name  # Add model name for reference
    results_df = pd.concat([results_df, pd.DataFrame([metrics])], ignore_index=True)

CPU times: total: 15.5 s
Wall time: 16.3 s

# Display the results DataFrame
results_df.sort_values(by="R2 Score", ascending=False)

results_df.sort_values(by="MAE")

results_df.sort_values(by="MSE")

results_df.sort_values(by="RMSE")

# Define the model with the selected hyperparameters
RandomForest = RandomForestRegressor()

# Train the model on the entire training dataset
RandomForest.fit(X_train, y_train)

# Feature importance
feature_importances = pd.Series(RandomForest.feature_importances_, index=X_train.columns)
feature_importances = feature_importances.sort_values(ascending=False)

# Plotting
plt.figure(figsize=(10, 6))
feature_importances.plot(kind='bar')
plt.title('Feature Importance')
plt.xlabel('Features')
plt.ylabel('Importance Score')
plt.show()

# Drop the constant column
X_train_vif = X_train.drop(columns=['const'])

vif_series = pd.Series(
    [variance_inflation_factor(X_train_vif.values, i) for i in range(X_train_vif.shape[1])],
    index=X_train_vif.columns,
    dtype=float,
)
print("Series before feature selection: \n\n{}\n".format(vif_series))

Series before feature selection: 

rooms                           11.080074
bathroom                        11.296229
lift                             3.449079
terrace                          1.346301
square_meters                    2.099052
square_meters_price              1.568111
real_state_attic                 1.352480
real_state_flat                  9.137370
real_state_study                 1.165991
neighborhood_Eixample            2.586087
neighborhood_Les Corts           1.328271
neighborhood_Sant Martí          1.425954
neighborhood_Ciutat Vella        1.887352
neighborhood_Gràcia              1.483803
neighborhood_Sants-Montjuïc      1.441272
neighborhood_Sant Andreu         1.144297
neighborhood_Horta- Guinardo     1.242755
neighborhood_Nou Barris          1.077936
dtype: float64

def preprocess_data(data, target_feature, drop_features, scale_features, test_size=0.30, random_state=1):
    """
    Preprocesses the dataset by handling categorical variables, boolean conversion,
    splitting data, transforming skewed features, standardizing, and adding a constant.
    
    Parameters:
    - data: DataFrame containing the full dataset.
    - target_feature: Name of the dependent variable.
    - drop_features: List of features to drop from the dataset.
    - scale_features: List of numerical features to transform and scale.
    - test_size: Proportion of the dataset to include in the test split.
    - random_state: Seed for reproducibility.
    
    Returns:
    - X_train, X_test, y_train, y_test: Processed training and test datasets.
    """
    # 1. Specify independent (X) and dependent (y) variables
    X = data.drop(drop_features, axis=1)
    y = data[target_feature]
    
    # 2. Create dummy variables for categorical features
    categorical_features = ['real_state', 'neighborhood']
    X = pd.get_dummies(X, columns=categorical_features, drop_first=True)
    
    # 3. Convert boolean columns to numeric (0 and 1)
    bool_cols = X.select_dtypes(['bool']).columns
    X[bool_cols] = X[bool_cols].astype(int)
    
    # 4. Split data into training and test sets
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_state)
    
    # 5. Transform and scale right-skewed variables (PowerTransformer for skewed data)
    pt = PowerTransformer(method='yeo-johnson')
    X_train[scale_features] = pt.fit_transform(X_train[scale_features])
    X_test[scale_features] = pt.transform(X_test[scale_features])
    
    # 6. Standardize the transformed numerical features
    scaler = StandardScaler()
    X_train[scale_features] = scaler.fit_transform(X_train[scale_features])
    X_test[scale_features] = scaler.transform(X_test[scale_features])
    
    # 7. Add a constant to independent variables (after scaling)
    X_train = sm.add_constant(X_train)
    X_test = sm.add_constant(X_test)
    
    return X_train, X_test, y_train, y_test

X_train, X_test, y_train, y_test= preprocess_data(data, ['price'], ['price','square_meters_price'], ['square_meters'], test_size=0.30, random_state=1)

# Initialize an empty DataFrame to store results
results_df = pd.DataFrame(columns=["Model", "MAE", "MSE", "RMSE", "R2 Score"])

%%time
# Loop through each model, train it, evaluate it, and store results
for model_name, model in regression_models.items():
    model.fit(X_train, y_train)
    metrics = evaluate_model(model, X_test, y_test)
    metrics["Model"] = model_name  # Add model name for reference
    results_df = pd.concat([results_df, pd.DataFrame([metrics])], ignore_index=True)

CPU times: total: 13.6 s
Wall time: 13.8 s

# Display the results DataFrame
results_df.sort_values(by="R2 Score", ascending=False)

# Drop the constant column
X_train_vif = X_train.drop(columns=['const'])

vif_series = pd.Series(
    [variance_inflation_factor(X_train_vif.values, i) for i in range(X_train_vif.shape[1])],
    index=X_train_vif.columns,
    dtype=float,
)
print("Series before feature selection: \n\n{}\n".format(vif_series))

Series before feature selection: 

rooms                           10.837814
bathroom                        10.048749
lift                             3.432845
terrace                          1.338510
square_meters                    1.609008
real_state_attic                 1.348520
real_state_flat                  8.486485
real_state_study                 1.147954
neighborhood_Eixample            2.580478
neighborhood_Les Corts           1.328092
neighborhood_Sant Martí          1.425753
neighborhood_Ciutat Vella        1.887234
neighborhood_Gràcia              1.483735
neighborhood_Sants-Montjuïc      1.439393
neighborhood_Sant Andreu         1.141826
neighborhood_Horta- Guinardo     1.235647
neighborhood_Nou Barris          1.075084
dtype: float64

X_train, X_test, y_train, y_test= preprocess_data(data, ['price'], ['price','square_meters_price','rooms'], ['square_meters'], test_size=0.30, random_state=1)

# Initialize an empty DataFrame to store results
results_df = pd.DataFrame(columns=["Model", "MAE", "MSE", "RMSE", "R2 Score"])

%%time
# Loop through each model, train it, evaluate it, and store results
for model_name, model in regression_models.items():
    model.fit(X_train, y_train)
    metrics = evaluate_model(model, X_test, y_test)
    metrics["Model"] = model_name  # Add model name for reference
    results_df = pd.concat([results_df, pd.DataFrame([metrics])], ignore_index=True)

CPU times: total: 13.2 s
Wall time: 13.5 s

# Display the results DataFrame
results_df.sort_values(by="R2 Score", ascending=False)

# Drop the constant column
X_train_vif = X_train.drop(columns=['const'])

vif_series = pd.Series(
    [variance_inflation_factor(X_train_vif.values, i) for i in range(X_train_vif.shape[1])],
    index=X_train_vif.columns,
    dtype=float,
)
print("Series before feature selection: \n\n{}\n".format(vif_series))

Series before feature selection: 

bathroom                        8.222008
lift                            3.418865
terrace                         1.338489
square_meters                   1.354581
real_state_attic                1.323041
real_state_flat                 7.304896
real_state_study                1.144434
neighborhood_Eixample           2.459688
neighborhood_Les Corts          1.300169
neighborhood_Sant Martí         1.382281
neighborhood_Ciutat Vella       1.849081
neighborhood_Gràcia             1.440009
neighborhood_Sants-Montjuïc     1.393866
neighborhood_Sant Andreu        1.121367
neighborhood_Horta- Guinardo    1.201621
neighborhood_Nou Barris         1.063670
dtype: float64

X_train, X_test, y_train, y_test= preprocess_data(data, ['price'], ['price','square_meters_price','rooms','bathroom'], ['square_meters'], test_size=0.30, random_state=1)

# Initialize an empty DataFrame to store results
results_df = pd.DataFrame(columns=["Model", "MAE", "MSE", "RMSE", "R2 Score"])

%%time
# Loop through each model, train it, evaluate it, and store results
for model_name, model in regression_models.items():
    model.fit(X_train, y_train)
    metrics = evaluate_model(model, X_test, y_test)
    metrics["Model"] = model_name  # Add model name for reference
    results_df = pd.concat([results_df, pd.DataFrame([metrics])], ignore_index=True)

CPU times: total: 13.5 s
Wall time: 14.5 s

# Display the results DataFrame
results_df.sort_values(by="R2 Score", ascending=False)

# Drop the constant column
X_train_vif = X_train.drop(columns=['const'])

vif_series = pd.Series(
    [variance_inflation_factor(X_train_vif.values, i) for i in range(X_train_vif.shape[1])],
    index=X_train_vif.columns,
    dtype=float,
)
print("Series before feature selection: \n\n{}\n".format(vif_series))

Series before feature selection: 

lift                            3.240716
terrace                         1.335683
square_meters                   1.100341
real_state_attic                1.259749
real_state_flat                 5.435033
real_state_study                1.099832
neighborhood_Eixample           2.160766
neighborhood_Les Corts          1.248794
neighborhood_Sant Martí         1.317437
neighborhood_Ciutat Vella       1.622886
neighborhood_Gràcia             1.365185
neighborhood_Sants-Montjuïc     1.317733
neighborhood_Sant Andreu        1.107205
neighborhood_Horta- Guinardo    1.170314
neighborhood_Nou Barris         1.056992
dtype: float64

def preprocess_data(data, target_feature, drop_features, scale_features, categorical_features, baseline_categories, test_size=0.30, random_state=1):
    """
    Preprocesses the dataset by handling categorical variables, boolean conversion,
    splitting data, transforming skewed features, standardizing, and adding a constant.
    
    Parameters:
    - data: DataFrame containing the full dataset.
    - target_feature: Name of the dependent variable.
    - drop_features: List of features to drop.
    - scale_features: List of numerical features to transform and scale.
    - categorical_features: List of categorical features to encode.
    - baseline_categories: Dictionary specifying baseline category for each categorical variable.
    - test_size: Proportion of the dataset to include in the test split.
    - random_state: Seed for reproducibility.
    
    Returns:
    - X_train, X_test, y_train, y_test: Processed training and test datasets.
    """
    # 1. Specify independent (X) and dependent (y) variables
    X = data.drop([target_feature] + drop_features, axis=1)
    y = data[target_feature]
    
    # 2. Create dummy variables for categorical features with specified baseline categories
    X = pd.get_dummies(X, columns=categorical_features, drop_first=False)
    for feature, baseline in baseline_categories.items():
        if f"{feature}_{baseline}" in X.columns:
            X.drop(columns=[f"{feature}_{baseline}"], inplace=True)
    
    # 3. Convert boolean columns to numeric (0 and 1)
    bool_cols = X.select_dtypes(['bool']).columns
    X[bool_cols] = X[bool_cols].astype(int)
    
    # 4. Split data into training and test sets
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, random_state=random_state)
    
    # 5. Transform and scale right-skewed variables (PowerTransformer for skewed data)
    pt = PowerTransformer(method='yeo-johnson')
    X_train[scale_features] = pt.fit_transform(X_train[scale_features])
    X_test[scale_features] = pt.transform(X_test[scale_features])
    
    # 6. Standardize the transformed numerical features
    scaler = StandardScaler()
    X_train[scale_features] = scaler.fit_transform(X_train[scale_features])
    X_test[scale_features] = scaler.transform(X_test[scale_features])
    
    # 7. Add a constant to independent variables (after scaling)
    X_train = sm.add_constant(X_train)
    X_test = sm.add_constant(X_test)
    
    return X_train, X_test, y_train, y_test

plot_crosstab_heat_perc(df6, var_interest='real_state',df_name="prepared data")

X_train, X_test, y_train, y_test = preprocess_data(
    data=data, 
    target_feature="price", 
    drop_features=["price", "square_meters_price", "rooms", "bathroom"],
    scale_features=["square_meters"], 
    categorical_features=["real_state", "neighborhood"], 
    baseline_categories={"real_state": "flat", "neighborhood": "Eixample"}, 
    test_size=0.30, 
    random_state=1
)

# Initialize an empty DataFrame to store results
results_df = pd.DataFrame(columns=["Model", "MAE", "MSE", "RMSE", "R2 Score"])

%%time
# Loop through each model, train it, evaluate it, and store results
for model_name, model in regression_models.items():
    model.fit(X_train, y_train)
    metrics = evaluate_model(model, X_test, y_test)
    metrics["Model"] = model_name  # Add model name for reference
    results_df = pd.concat([results_df, pd.DataFrame([metrics])], ignore_index=True)

CPU times: total: 15.8 s
Wall time: 18.2 s

# Display the results DataFrame
results_df.sort_values(by="R2 Score", ascending=False)

# Drop the constant column
X_train_vif = X_train.drop(columns=['const'])

vif_series = pd.Series(
    [variance_inflation_factor(X_train_vif.values, i) for i in range(X_train_vif.shape[1])],
    index=X_train_vif.columns,
    dtype=float,
)
print("Series before feature selection: \n\n{}\n".format(vif_series))

Series before feature selection: 

lift                                2.020784
terrace                             1.325467
square_meters                       1.103906
real_state_apartment                1.082000
real_state_attic                    1.093367
real_state_study                    1.049390
neighborhood_Sarria-Sant Gervasi    1.255990
neighborhood_Les Corts              1.098590
neighborhood_Sant Martí             1.121619
neighborhood_Ciutat Vella           1.207858
neighborhood_Gràcia                 1.118434
neighborhood_Sants-Montjuïc         1.105899
neighborhood_Sant Andreu            1.037034
neighborhood_Horta- Guinardo        1.053019
neighborhood_Nou Barris             1.018164
dtype: float64

# Define a dictionary of regression models
regression_models_2 = {
    "DecisionTree_Tuned_1": DecisionTreeRegressor(max_depth=10, min_samples_split=5),
    "RandomForest_Tuned_1": RandomForestRegressor(max_depth=10, min_samples_split=5, n_estimators=200),
    "GradientBoosting_Tuned_1": GradientBoostingRegressor(n_estimators=200, learning_rate=0.1, max_depth=5),
    "XGBoost_Tuned_1": xgb.XGBRegressor(n_estimators=200, learning_rate=0.1, max_depth=5),
    "LightGBM_Tuned_1": lgb.LGBMRegressor(n_estimators=200, learning_rate=0.1, max_depth=5, verbose=-1),
    #"CatBoost": catb.CatBoostRegressor(iterations=200, learning_rate=0.1, depth=5, verbose=0),
    "NeuralNetwork(MLP)": MLPRegressor(hidden_layer_sizes=(100,), activation='relu', solver='adam', max_iter=500)
}

# Initialize an empty DataFrame to store results
results_df_2 = pd.DataFrame(columns=["Model", "MAE", "MSE", "RMSE", "R2 Score"])

%%time
# Loop through each model, train it, evaluate it, and store results
for model_name, model in regression_models_2.items():
    model.fit(X_train, y_train)
    metrics = evaluate_model(model, X_test, y_test)
    metrics["Model"] = model_name  # Add model name for reference
    results_df_2 = pd.concat([results_df_2, pd.DataFrame([metrics])], ignore_index=True)

CPU times: total: 19.7 s
Wall time: 19.5 s

# Display the results DataFrame
results_df_2.sort_values(by="R2 Score", ascending=False)

# Display the results DataFrame
results_df.sort_values(by="R2 Score", ascending=False)

def tune_gradient_boosting():
    print("Tuning Gradient Boosting...")
    param_grid = {
        'n_estimators': [100, 200, 300, 500],
        'learning_rate': [0.01, 0.05, 0.1, 0.2],
        'max_depth': [3, 5, 7, 9],
        'min_samples_split': [2, 5, 10],
        'min_samples_leaf': [1, 2, 4],
        'subsample': [0.8, 0.9, 1.0],
        'max_features': ['sqrt', 'log2', None]
    }
    
    gb = GradientBoostingRegressor(random_state=42)
    grid_search = RandomizedSearchCV(
        estimator=gb,
        param_distributions=param_grid,
        n_iter=20,
        cv=5,
        scoring='r2',
        n_jobs=-1,
        random_state=42,
        verbose=1
    )
    
    grid_search.fit(X_train, y_train)
    print(f"Best parameters: {grid_search.best_params_}")
    print(f"Best R2 score: {grid_search.best_score_:.4f}")
    best_gb = grid_search.best_estimator_
    
    return best_gb

tune_gradient_boosting()

Tuning Gradient Boosting...
Fitting 5 folds for each of 20 candidates, totalling 100 fits
Best parameters: {'subsample': 0.8, 'n_estimators': 100, 'min_samples_split': 10, 'min_samples_leaf': 4, 'max_features': None, 'max_depth': 3, 'learning_rate': 0.1}
Best R2 score: 0.5434

GradientBoostingRegressor(min_samples_leaf=4, min_samples_split=10,
                          random_state=42, subsample=0.8)

GradientBoostingRegressor(min_samples_leaf=4, min_samples_split=10,
                          random_state=42, subsample=0.8)

def tune_xgboost():
    print("Tuning XGBoost...")
    param_grid = {
        'n_estimators': [100, 200, 300, 500],
        'learning_rate': [0.01, 0.05, 0.1, 0.2],
        'max_depth': [3, 5, 7, 9],
        'min_child_weight': [1, 3, 5, 7],
        'gamma': [0, 0.1, 0.2, 0.3],
        'subsample': [0.6, 0.8, 1.0],
        'colsample_bytree': [0.6, 0.8, 1.0],
        'reg_alpha': [0, 0.1, 1, 10],
        'reg_lambda': [0, 1, 5, 10]
    }
    
    xgb_model = xgb.XGBRegressor(random_state=42)
    grid_search = RandomizedSearchCV(
        estimator=xgb_model,
        param_distributions=param_grid,
        n_iter=20,
        cv=5,
        scoring='r2',
        n_jobs=-1,
        random_state=42,
        verbose=1
    )
    
    grid_search.fit(X_train, y_train)
    print(f"Best parameters: {grid_search.best_params_}")
    print(f"Best R2 score: {grid_search.best_score_:.4f}")
    
    best_xgb = grid_search.best_estimator_
    return best_xgb

tune_xgboost()

Tuning XGBoost...
Fitting 5 folds for each of 20 candidates, totalling 100 fits

Best parameters: {'subsample': 0.6, 'reg_lambda': 0, 'reg_alpha': 10, 'n_estimators': 500, 'min_child_weight': 3, 'max_depth': 3, 'learning_rate': 0.05, 'gamma': 0.2, 'colsample_bytree': 1.0}
Best R2 score: 0.5456

XGBRegressor(base_score=None, booster=None, callbacks=None,
             colsample_bylevel=None, colsample_bynode=None,
             colsample_bytree=1.0, device=None, early_stopping_rounds=None,
             enable_categorical=False, eval_metric=None, feature_types=None,
             gamma=0.2, grow_policy=None, importance_type=None,
             interaction_constraints=None, learning_rate=0.05, max_bin=None,
             max_cat_threshold=None, max_cat_to_onehot=None,
             max_delta_step=None, max_depth=3, max_leaves=None,
             min_child_weight=3, missing=nan, monotone_constraints=None,
             multi_strategy=None, n_estimators=500, n_jobs=None,
             num_parallel_tree=None, random_state=42, ...)

XGBRegressor(base_score=None, booster=None, callbacks=None,
             colsample_bylevel=None, colsample_bynode=None,
             colsample_bytree=1.0, device=None, early_stopping_rounds=None,
             enable_categorical=False, eval_metric=None, feature_types=None,
             gamma=0.2, grow_policy=None, importance_type=None,
             interaction_constraints=None, learning_rate=0.05, max_bin=None,
             max_cat_threshold=None, max_cat_to_onehot=None,
             max_delta_step=None, max_depth=3, max_leaves=None,
             min_child_weight=3, missing=nan, monotone_constraints=None,
             multi_strategy=None, n_estimators=500, n_jobs=None,
             num_parallel_tree=None, random_state=42, ...)

def tune_lightgbm():
    print("Tuning LightGBM...")
    param_grid = {
        'n_estimators': [100, 200, 300, 500],
        'learning_rate': [0.01, 0.05, 0.1, 0.2],
        'max_depth': [3, 5, 7, 9, -1],
        'num_leaves': [31, 50, 100, 150],
        'min_child_samples': [5, 10, 20, 50],
        'subsample': [0.6, 0.8, 1.0],
        'colsample_bytree': [0.6, 0.8, 1.0],
        'reg_alpha': [0, 0.1, 1, 10],
        'reg_lambda': [0, 1, 5, 10]
    }
    
    lgb_model = lgb.LGBMRegressor(random_state=42, verbose=-1)
    grid_search = RandomizedSearchCV(
        estimator=lgb_model,
        param_distributions=param_grid,
        n_iter=20,
        cv=5,
        scoring='r2',
        n_jobs=-1,
        random_state=42,
        verbose=1
    )
    
    grid_search.fit(X_train, y_train)
    print(f"Best parameters: {grid_search.best_params_}")
    print(f"Best R2 score: {grid_search.best_score_:.4f}")
    
    best_lgb = grid_search.best_estimator_
    return best_lgb

tune_lightgbm()

Tuning LightGBM...
Fitting 5 folds for each of 20 candidates, totalling 100 fits
Best parameters: {'subsample': 0.6, 'reg_lambda': 1, 'reg_alpha': 10, 'num_leaves': 50, 'n_estimators': 500, 'min_child_samples': 5, 'max_depth': 3, 'learning_rate': 0.05, 'colsample_bytree': 0.6}
Best R2 score: 0.5443

LGBMRegressor(colsample_bytree=0.6, learning_rate=0.05, max_depth=3,
              min_child_samples=5, n_estimators=500, num_leaves=50,
              random_state=42, reg_alpha=10, reg_lambda=1, subsample=0.6,
              verbose=-1)

LGBMRegressor(colsample_bytree=0.6, learning_rate=0.05, max_depth=3,
              min_child_samples=5, n_estimators=500, num_leaves=50,
              random_state=42, reg_alpha=10, reg_lambda=1, subsample=0.6,
              verbose=-1)

import optuna

# ===============================================
# Advanced Hyperparameter Tuning with Optuna
# ===============================================

def tune_with_optuna(model_type):
    print(f"Tuning {model_type} with Optuna...")
    
    def objective(trial):
        if model_type == 'xgboost':
            params = {
                'n_estimators': trial.suggest_int('n_estimators', 100, 1000),
                'learning_rate': trial.suggest_float('learning_rate', 0.01, 0.3),
                'max_depth': trial.suggest_int('max_depth', 3, 10),
                'min_child_weight': trial.suggest_int('min_child_weight', 1, 10),
                'gamma': trial.suggest_float('gamma', 0, 1),
                'subsample': trial.suggest_float('subsample', 0.5, 1.0),
                'colsample_bytree': trial.suggest_float('colsample_bytree', 0.5, 1.0),
                'reg_alpha': trial.suggest_float('reg_alpha', 0, 10),
                'reg_lambda': trial.suggest_float('reg_lambda', 0, 10),
                'random_state': 42
            }
            model = xgb.XGBRegressor(**params)
        
        elif model_type == 'lightgbm':
            params = {
                'n_estimators': trial.suggest_int('n_estimators', 100, 1000),
                'learning_rate': trial.suggest_float('learning_rate', 0.01, 0.3),
                'max_depth': trial.suggest_int('max_depth', 3, 10),
                'num_leaves': trial.suggest_int('num_leaves', 20, 200),
                'min_child_samples': trial.suggest_int('min_child_samples', 5, 100),
                'subsample': trial.suggest_float('subsample', 0.5, 1.0),
                'colsample_bytree': trial.suggest_float('colsample_bytree', 0.5, 1.0),
                'reg_alpha': trial.suggest_float('reg_alpha', 0, 10),
                'reg_lambda': trial.suggest_float('reg_lambda', 0, 10),
                'random_state': 42,
                'verbose': -1
            }
            model = lgb.LGBMRegressor(**params)
        
        elif model_type == 'gbr':
            params = {
                'n_estimators': trial.suggest_int('n_estimators', 100, 1000),
                'learning_rate': trial.suggest_float('learning_rate', 0.01, 0.3),
                'max_depth': trial.suggest_int('max_depth', 3, 10),
                'min_samples_split': trial.suggest_int('min_samples_split', 2, 20),
                'min_samples_leaf': trial.suggest_int('min_samples_leaf', 1, 10),
                'subsample': trial.suggest_float('subsample', 0.5, 1.0),
                'max_features': trial.suggest_categorical('max_features', ['sqrt', 'log2', None]),
                'random_state': 42
            }
            model = GradientBoostingRegressor(**params)
        
        else:
            raise ValueError(f"Unknown model type: {model_type}")
            
        # Use cross-validation for more robust evaluation
        kf = KFold(n_splits=5, shuffle=True, random_state=42)
        scores = cross_val_score(model, X_train, y_train, cv=kf, scoring='r2')
        return scores.mean()
    
    # Create and optimize the study
    study = optuna.create_study(direction='maximize')
    study.optimize(objective, n_trials=50)
    
    print(f"Best trial: {study.best_trial.number}")
    print(f"Best R2 score: {study.best_value:.4f}")
    print(f"Best parameters: {study.best_params}")
    
    # Create a model with the best parameters
    if model_type == 'xgboost':
        best_model = xgb.XGBRegressor(**study.best_params)
    elif model_type == 'lightgbm':
        best_model = lgb.LGBMRegressor(**study.best_params)
    elif model_type == 'gbr':
        best_model = GradientBoostingRegressor(**study.best_params)
    
    # Train and evaluate on test set
    best_model.fit(X_train, y_train)
    #metrics = evaluate_model(best_model, X_train, X_test, y_train, y_test)
    #print(f"Test R2 score: {metrics['R2 Score']:.4f}")
    
    return best_model

tune_with_optuna('xgboost')

[I 2025-02-28 18:26:08,821] A new study created in memory with name: no-name-c3bea523-3901-49e5-bc06-10a192dccd4c

Tuning xgboost with Optuna...

[I 2025-02-28 18:26:24,163] Trial 0 finished with value: 0.48917752504348755 and parameters: {'n_estimators': 888, 'learning_rate': 0.13638048024350496, 'max_depth': 8, 'min_child_weight': 8, 'gamma': 0.06434676023791375, 'subsample': 0.7165790736450253, 'colsample_bytree': 0.5121990183798227, 'reg_alpha': 5.746612857926817, 'reg_lambda': 6.923761570557943}. Best is trial 0 with value: 0.48917752504348755.
[I 2025-02-28 18:26:30,704] Trial 1 finished with value: 0.48238654136657716 and parameters: {'n_estimators': 393, 'learning_rate': 0.09384983663772839, 'max_depth': 10, 'min_child_weight': 4, 'gamma': 0.5514728804308722, 'subsample': 0.5981765793087479, 'colsample_bytree': 0.8075428855306195, 'reg_alpha': 9.307261576083217, 'reg_lambda': 7.241394804967402}. Best is trial 0 with value: 0.48917752504348755.
[I 2025-02-28 18:26:34,803] Trial 2 finished with value: 0.5223005294799805 and parameters: {'n_estimators': 407, 'learning_rate': 0.11871603858664527, 'max_depth': 6, 'min_child_weight': 2, 'gamma': 0.6967152026076723, 'subsample': 0.8846920736377173, 'colsample_bytree': 0.5133437318094024, 'reg_alpha': 0.8649785036720237, 'reg_lambda': 5.878119849951487}. Best is trial 2 with value: 0.5223005294799805.
[I 2025-02-28 18:26:40,994] Trial 3 finished with value: 0.50477694272995 and parameters: {'n_estimators': 665, 'learning_rate': 0.15214036925300578, 'max_depth': 7, 'min_child_weight': 8, 'gamma': 0.9031770410225999, 'subsample': 0.681241311018806, 'colsample_bytree': 0.5141291135344452, 'reg_alpha': 4.33395472050038, 'reg_lambda': 9.411524376239278}. Best is trial 2 with value: 0.5223005294799805.
[I 2025-02-28 18:26:45,903] Trial 4 finished with value: 0.5029198408126831 and parameters: {'n_estimators': 700, 'learning_rate': 0.2995516278226636, 'max_depth': 4, 'min_child_weight': 3, 'gamma': 0.1306726528413399, 'subsample': 0.9542975672262177, 'colsample_bytree': 0.747427421816002, 'reg_alpha': 2.987130049785515, 'reg_lambda': 3.2037729939708024}. Best is trial 2 with value: 0.5223005294799805.
[I 2025-02-28 18:26:52,834] Trial 5 finished with value: 0.42719292640686035 and parameters: {'n_estimators': 674, 'learning_rate': 0.29003915104330136, 'max_depth': 6, 'min_child_weight': 3, 'gamma': 0.9274640608616926, 'subsample': 0.988081540402282, 'colsample_bytree': 0.8941856867048612, 'reg_alpha': 0.3263042730315746, 'reg_lambda': 1.4852147107431324}. Best is trial 2 with value: 0.5223005294799805.
[I 2025-02-28 18:27:01,629] Trial 6 finished with value: 0.4879873275756836 and parameters: {'n_estimators': 952, 'learning_rate': 0.15389715502445497, 'max_depth': 6, 'min_child_weight': 5, 'gamma': 0.9090277514328283, 'subsample': 0.897013687505599, 'colsample_bytree': 0.5050074177242521, 'reg_alpha': 4.353580911570742, 'reg_lambda': 1.4369264223904599}. Best is trial 2 with value: 0.5223005294799805.
[I 2025-02-28 18:27:04,869] Trial 7 finished with value: 0.5319819688796997 and parameters: {'n_estimators': 421, 'learning_rate': 0.2022139181760185, 'max_depth': 3, 'min_child_weight': 2, 'gamma': 0.9147586121490527, 'subsample': 0.6467542388459349, 'colsample_bytree': 0.9331485843647656, 'reg_alpha': 5.870927504162713, 'reg_lambda': 7.474268183728644}. Best is trial 7 with value: 0.5319819688796997.
[I 2025-02-28 18:27:06,070] Trial 8 finished with value: 0.543352198600769 and parameters: {'n_estimators': 168, 'learning_rate': 0.07709481416442678, 'max_depth': 3, 'min_child_weight': 6, 'gamma': 0.6179366698460165, 'subsample': 0.6278972757798043, 'colsample_bytree': 0.8190965895343418, 'reg_alpha': 5.518448204079417, 'reg_lambda': 2.9877500989676453}. Best is trial 8 with value: 0.543352198600769.
[I 2025-02-28 18:27:17,093] Trial 9 finished with value: 0.44873361587524413 and parameters: {'n_estimators': 866, 'learning_rate': 0.1516948752160496, 'max_depth': 9, 'min_child_weight': 9, 'gamma': 0.6178197494002838, 'subsample': 0.9407339655954512, 'colsample_bytree': 0.6605986109530679, 'reg_alpha': 6.500892125923215, 'reg_lambda': 0.03437041373199001}. Best is trial 8 with value: 0.543352198600769.
[I 2025-02-28 18:27:18,599] Trial 10 finished with value: 0.5331526756286621 and parameters: {'n_estimators': 137, 'learning_rate': 0.02033192710934223, 'max_depth': 4, 'min_child_weight': 6, 'gamma': 0.292620892412038, 'subsample': 0.5216325280362273, 'colsample_bytree': 0.9840773811906716, 'reg_alpha': 8.155834349462769, 'reg_lambda': 3.9360639171120804}. Best is trial 8 with value: 0.543352198600769.
[I 2025-02-28 18:27:19,931] Trial 11 finished with value: 0.45643426179885865 and parameters: {'n_estimators': 106, 'learning_rate': 0.010488983845342616, 'max_depth': 4, 'min_child_weight': 6, 'gamma': 0.3049572471854668, 'subsample': 0.520442469968559, 'colsample_bytree': 0.9999609534850513, 'reg_alpha': 8.468519779713077, 'reg_lambda': 3.9708718272349968}. Best is trial 8 with value: 0.543352198600769.
[I 2025-02-28 18:27:21,183] Trial 12 finished with value: 0.5151201605796814 and parameters: {'n_estimators': 100, 'learning_rate': 0.025399498046396247, 'max_depth': 3, 'min_child_weight': 6, 'gamma': 0.36416676033415973, 'subsample': 0.5411003789643622, 'colsample_bytree': 0.8339552529517178, 'reg_alpha': 7.700643593211, 'reg_lambda': 4.036221719845212}. Best is trial 8 with value: 0.543352198600769.
[I 2025-02-28 18:27:23,985] Trial 13 finished with value: 0.5437254309654236 and parameters: {'n_estimators': 250, 'learning_rate': 0.06693226182648743, 'max_depth': 4, 'min_child_weight': 7, 'gamma': 0.3696765199367511, 'subsample': 0.794711808518893, 'colsample_bytree': 0.6865005344815053, 'reg_alpha': 9.910407108713995, 'reg_lambda': 2.2326642799541316}. Best is trial 13 with value: 0.5437254309654236.
[I 2025-02-28 18:27:26,539] Trial 14 finished with value: 0.5405412554740906 and parameters: {'n_estimators': 263, 'learning_rate': 0.06381385702672845, 'max_depth': 5, 'min_child_weight': 8, 'gamma': 0.4287584297754668, 'subsample': 0.8042622571793558, 'colsample_bytree': 0.6715707976463381, 'reg_alpha': 2.5083568190792556, 'reg_lambda': 2.2601519358002795}. Best is trial 13 with value: 0.5437254309654236.
[I 2025-02-28 18:27:28,581] Trial 15 finished with value: 0.5440799832344055 and parameters: {'n_estimators': 244, 'learning_rate': 0.07041223547960868, 'max_depth': 3, 'min_child_weight': 10, 'gamma': 0.7197881334465857, 'subsample': 0.7779178290732698, 'colsample_bytree': 0.679125411798041, 'reg_alpha': 9.569034426519458, 'reg_lambda': 0.12279704257417778}. Best is trial 15 with value: 0.5440799832344055.
[I 2025-02-28 18:27:31,539] Trial 16 finished with value: 0.540407121181488 and parameters: {'n_estimators': 275, 'learning_rate': 0.06063294345361731, 'max_depth': 5, 'min_child_weight': 10, 'gamma': 0.7365524645454472, 'subsample': 0.8110906118418999, 'colsample_bytree': 0.623141542992063, 'reg_alpha': 9.781172279316053, 'reg_lambda': 0.43143826902046456}. Best is trial 15 with value: 0.5440799832344055.
[I 2025-02-28 18:27:37,498] Trial 17 finished with value: 0.5101608753204345 and parameters: {'n_estimators': 537, 'learning_rate': 0.19241134263140267, 'max_depth': 5, 'min_child_weight': 10, 'gamma': 0.7467361833627015, 'subsample': 0.7717331640243381, 'colsample_bytree': 0.7264319782750525, 'reg_alpha': 7.115478280534627, 'reg_lambda': 1.1523235971868167}. Best is trial 15 with value: 0.5440799832344055.
[I 2025-02-28 18:27:40,731] Trial 18 finished with value: 0.5394483804702759 and parameters: {'n_estimators': 285, 'learning_rate': 0.10229676823863273, 'max_depth': 4, 'min_child_weight': 7, 'gamma': 0.18883282239766835, 'subsample': 0.8371227008001572, 'colsample_bytree': 0.5736934015173419, 'reg_alpha': 9.06265115610064, 'reg_lambda': 2.3752129472463364}. Best is trial 15 with value: 0.5440799832344055.
[I 2025-02-28 18:27:44,909] Trial 19 finished with value: 0.5307446241378784 and parameters: {'n_estimators': 500, 'learning_rate': 0.20147488495809995, 'max_depth': 3, 'min_child_weight': 9, 'gamma': 0.474104213089799, 'subsample': 0.7372191544654088, 'colsample_bytree': 0.6913039115734858, 'reg_alpha': 9.67396253041139, 'reg_lambda': 5.127762143253605}. Best is trial 15 with value: 0.5440799832344055.
[I 2025-02-28 18:27:51,513] Trial 20 finished with value: 0.5363608479499817 and parameters: {'n_estimators': 208, 'learning_rate': 0.04951744310034004, 'max_depth': 7, 'min_child_weight': 9, 'gamma': 0.8011995402540919, 'subsample': 0.8614635610779272, 'colsample_bytree': 0.6017936502418365, 'reg_alpha': 7.17655323116587, 'reg_lambda': 0.9345585130656484}. Best is trial 15 with value: 0.5440799832344055.
[I 2025-02-28 18:27:54,395] Trial 21 finished with value: 0.5442478656768799 and parameters: {'n_estimators': 206, 'learning_rate': 0.08027934373962738, 'max_depth': 3, 'min_child_weight': 5, 'gamma': 0.5832246430248952, 'subsample': 0.6088060632152655, 'colsample_bytree': 0.7688938558463965, 'reg_alpha': 8.550184417955817, 'reg_lambda': 2.4928865849773194}. Best is trial 21 with value: 0.5442478656768799.
[I 2025-02-28 18:27:57,272] Trial 22 finished with value: 0.5443528175354004 and parameters: {'n_estimators': 345, 'learning_rate': 0.045342520753788654, 'max_depth': 3, 'min_child_weight': 4, 'gamma': 0.5383740706117337, 'subsample': 0.7662572032520517, 'colsample_bytree': 0.7860995489943112, 'reg_alpha': 8.46310279421163, 'reg_lambda': 2.1457065169311202}. Best is trial 22 with value: 0.5443528175354004.
[I 2025-02-28 18:28:02,431] Trial 23 finished with value: 0.5443742871284485 and parameters: {'n_estimators': 330, 'learning_rate': 0.03571713088640459, 'max_depth': 3, 'min_child_weight': 4, 'gamma': 0.5732685763841034, 'subsample': 0.6996412869755224, 'colsample_bytree': 0.7790660629800674, 'reg_alpha': 8.540430721935605, 'reg_lambda': 0.44990861881143535}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:28:05,876] Trial 24 finished with value: 0.5413497686386108 and parameters: {'n_estimators': 333, 'learning_rate': 0.03769392614153432, 'max_depth': 5, 'min_child_weight': 4, 'gamma': 0.5418371091725079, 'subsample': 0.6964528442045947, 'colsample_bytree': 0.7945786585066853, 'reg_alpha': 8.383487409926348, 'reg_lambda': 1.801227606365993}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:28:08,732] Trial 25 finished with value: 0.5407013773918152 and parameters: {'n_estimators': 360, 'learning_rate': 0.09383578193395664, 'max_depth': 3, 'min_child_weight': 4, 'gamma': 0.6247167867730725, 'subsample': 0.5759352383219941, 'colsample_bytree': 0.8604555455328667, 'reg_alpha': 7.284304617819455, 'reg_lambda': 3.08121700847077}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:28:27,239] Trial 26 finished with value: 0.5425023078918457 and parameters: {'n_estimators': 495, 'learning_rate': 0.03787779577950362, 'max_depth': 4, 'min_child_weight': 1, 'gamma': 0.491130039215511, 'subsample': 0.6594479465952411, 'colsample_bytree': 0.7750836297619202, 'reg_alpha': 8.680157456203698, 'reg_lambda': 5.495900414210266}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:28:30,868] Trial 27 finished with value: 0.53933265209198 and parameters: {'n_estimators': 335, 'learning_rate': 0.11736887581400667, 'max_depth': 3, 'min_child_weight': 5, 'gamma': 0.8187516904595493, 'subsample': 0.6099484443041393, 'colsample_bytree': 0.7510271924612915, 'reg_alpha': 6.49646428578942, 'reg_lambda': 0.7222028147330706}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:28:37,908] Trial 28 finished with value: 0.5147324204444885 and parameters: {'n_estimators': 195, 'learning_rate': 0.2434738648611366, 'max_depth': 5, 'min_child_weight': 3, 'gamma': 0.5672785585569524, 'subsample': 0.7457721548104954, 'colsample_bytree': 0.8683547328377962, 'reg_alpha': 7.924664906694303, 'reg_lambda': 4.253379164204221}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:28:44,959] Trial 29 finished with value: 0.5225183486938476 and parameters: {'n_estimators': 456, 'learning_rate': 0.04218092096635758, 'max_depth': 8, 'min_child_weight': 5, 'gamma': 0.4394513927468202, 'subsample': 0.7209905487524098, 'colsample_bytree': 0.7212782184436121, 'reg_alpha': 6.447263727827733, 'reg_lambda': 6.134843023455369}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:28:48,194] Trial 30 finished with value: 0.5387687802314758 and parameters: {'n_estimators': 335, 'learning_rate': 0.08359348295281316, 'max_depth': 4, 'min_child_weight': 4, 'gamma': 0.6561493506066338, 'subsample': 0.5666550463672569, 'colsample_bytree': 0.7727076033000955, 'reg_alpha': 8.884417845650987, 'reg_lambda': 2.787253390415141}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:28:50,377] Trial 31 finished with value: 0.542467987537384 and parameters: {'n_estimators': 213, 'learning_rate': 0.12546995609031303, 'max_depth': 3, 'min_child_weight': 5, 'gamma': 0.6939132860420116, 'subsample': 0.7669770160461884, 'colsample_bytree': 0.7183955636632947, 'reg_alpha': 9.257910968739045, 'reg_lambda': 0.20156358306157268}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:28:55,319] Trial 32 finished with value: 0.5410897016525269 and parameters: {'n_estimators': 616, 'learning_rate': 0.05792957787817061, 'max_depth': 3, 'min_child_weight': 7, 'gamma': 0.5528689548586072, 'subsample': 0.6900205440050493, 'colsample_bytree': 0.6456551256638154, 'reg_alpha': 7.692909838687805, 'reg_lambda': 0.6841492551333954}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:29:02,763] Trial 33 finished with value: 0.45999300479888916 and parameters: {'n_estimators': 308, 'learning_rate': 0.10644845581984247, 'max_depth': 10, 'min_child_weight': 3, 'gamma': 0.8378298041242138, 'subsample': 0.7133136650658649, 'colsample_bytree': 0.7869546343704892, 'reg_alpha': 9.23133982282121, 'reg_lambda': 1.7464679446487787}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:29:05,964] Trial 34 finished with value: 0.5420541644096375 and parameters: {'n_estimators': 375, 'learning_rate': 0.07945091367909182, 'max_depth': 3, 'min_child_weight': 2, 'gamma': 0.025209625162848415, 'subsample': 0.7800664113430529, 'colsample_bytree': 0.8468592096780337, 'reg_alpha': 8.91771014584181, 'reg_lambda': 0.05031391603297647}. Best is trial 23 with value: 0.5443742871284485.
[I 2025-02-28 18:29:09,280] Trial 35 finished with value: 0.5453838586807251 and parameters: {'n_estimators': 432, 'learning_rate': 0.025260200065027993, 'max_depth': 4, 'min_child_weight': 4, 'gamma': 0.7006081302005231, 'subsample': 0.6528657324270758, 'colsample_bytree': 0.7493578971046945, 'reg_alpha': 9.886845445607618, 'reg_lambda': 1.1707680158620883}. Best is trial 35 with value: 0.5453838586807251.
[I 2025-02-28 18:29:12,614] Trial 36 finished with value: 0.5451103687286377 and parameters: {'n_estimators': 443, 'learning_rate': 0.02721077650020993, 'max_depth': 4, 'min_child_weight': 4, 'gamma': 0.5700620659878068, 'subsample': 0.6460465525980261, 'colsample_bytree': 0.7552232657580044, 'reg_alpha': 8.443426859500827, 'reg_lambda': 8.766885625636503}. Best is trial 35 with value: 0.5453838586807251.
[I 2025-02-28 18:29:16,873] Trial 37 finished with value: 0.545316469669342 and parameters: {'n_estimators': 445, 'learning_rate': 0.014051132538417561, 'max_depth': 4, 'min_child_weight': 4, 'gamma': 0.9977188285355159, 'subsample': 0.665005073625462, 'colsample_bytree': 0.8194604822600398, 'reg_alpha': 3.3097653447085658, 'reg_lambda': 9.318801375913448}. Best is trial 35 with value: 0.5453838586807251.
[I 2025-02-28 18:29:24,307] Trial 38 finished with value: 0.5432230710983277 and parameters: {'n_estimators': 616, 'learning_rate': 0.012728732176007318, 'max_depth': 6, 'min_child_weight': 3, 'gamma': 0.78526687548439, 'subsample': 0.6599673073106239, 'colsample_bytree': 0.9013964364712058, 'reg_alpha': 2.6688855103571254, 'reg_lambda': 9.683807813252347}. Best is trial 35 with value: 0.5453838586807251.
[I 2025-02-28 18:29:29,578] Trial 39 finished with value: 0.5448433876037597 and parameters: {'n_estimators': 424, 'learning_rate': 0.03178572220544605, 'max_depth': 4, 'min_child_weight': 4, 'gamma': 0.975911918061199, 'subsample': 0.6436148191741508, 'colsample_bytree': 0.8176649964963084, 'reg_alpha': 3.743006884808041, 'reg_lambda': 8.864779494401295}. Best is trial 35 with value: 0.5453838586807251.
[I 2025-02-28 18:29:46,659] Trial 40 finished with value: 0.5420290708541871 and parameters: {'n_estimators': 438, 'learning_rate': 0.030064471131231757, 'max_depth': 5, 'min_child_weight': 1, 'gamma': 0.9915905148295727, 'subsample': 0.6442874248620128, 'colsample_bytree': 0.8226221366239665, 'reg_alpha': 3.4700168401844587, 'reg_lambda': 8.777796041462576}. Best is trial 35 with value: 0.5453838586807251.
[I 2025-02-28 18:29:51,130] Trial 41 finished with value: 0.5458519577980041 and parameters: {'n_estimators': 403, 'learning_rate': 0.025181939608234893, 'max_depth': 4, 'min_child_weight': 2, 'gamma': 0.9450617049891935, 'subsample': 0.6775014498470824, 'colsample_bytree': 0.7494749285293014, 'reg_alpha': 1.605804505030021, 'reg_lambda': 8.650350883129157}. Best is trial 41 with value: 0.5458519577980041.
[I 2025-02-28 18:29:55,292] Trial 42 finished with value: 0.545633852481842 and parameters: {'n_estimators': 569, 'learning_rate': 0.023855296802388265, 'max_depth': 4, 'min_child_weight': 2, 'gamma': 0.9890646565353011, 'subsample': 0.6669536484875446, 'colsample_bytree': 0.7424051756638951, 'reg_alpha': 1.5819971923894427, 'reg_lambda': 8.381041733267152}. Best is trial 41 with value: 0.5458519577980041.
[I 2025-02-28 18:30:01,203] Trial 43 finished with value: 0.5420405983924865 and parameters: {'n_estimators': 618, 'learning_rate': 0.01723386549535197, 'max_depth': 6, 'min_child_weight': 2, 'gamma': 0.8546734957885499, 'subsample': 0.668317819630224, 'colsample_bytree': 0.7437699757132172, 'reg_alpha': 1.329928302833131, 'reg_lambda': 7.7227282297985225}. Best is trial 41 with value: 0.5458519577980041.
[I 2025-02-28 18:30:05,770] Trial 44 finished with value: 0.5408416152000427 and parameters: {'n_estimators': 534, 'learning_rate': 0.05016731777932866, 'max_depth': 4, 'min_child_weight': 2, 'gamma': 0.8835635709906183, 'subsample': 0.6280066678165979, 'colsample_bytree': 0.7088640020832621, 'reg_alpha': 1.5477380341377909, 'reg_lambda': 8.21794504715965}. Best is trial 41 with value: 0.5458519577980041.
[I 2025-02-28 18:30:12,207] Trial 45 finished with value: 0.5454214453697205 and parameters: {'n_estimators': 763, 'learning_rate': 0.011788495314032659, 'max_depth': 5, 'min_child_weight': 3, 'gamma': 0.9478992875376774, 'subsample': 0.5795941144840977, 'colsample_bytree': 0.7409612230172122, 'reg_alpha': 0.482345262428165, 'reg_lambda': 6.716675509475262}. Best is trial 41 with value: 0.5458519577980041.
[I 2025-02-28 18:30:18,688] Trial 46 finished with value: 0.5449263453483582 and parameters: {'n_estimators': 798, 'learning_rate': 0.012899785159010545, 'max_depth': 5, 'min_child_weight': 1, 'gamma': 0.9487509035940388, 'subsample': 0.5764018864860738, 'colsample_bytree': 0.7392979778285507, 'reg_alpha': 0.05638133810238344, 'reg_lambda': 6.6210598087435315}. Best is trial 41 with value: 0.5458519577980041.
[I 2025-02-28 18:30:25,159] Trial 47 finished with value: 0.5420300960540771 and parameters: {'n_estimators': 732, 'learning_rate': 0.02075742254358072, 'max_depth': 5, 'min_child_weight': 3, 'gamma': 0.9425923194929283, 'subsample': 0.5504265237884219, 'colsample_bytree': 0.7056346692644623, 'reg_alpha': 1.9886329876252316, 'reg_lambda': 7.099955651679609}. Best is trial 41 with value: 0.5458519577980041.
[I 2025-02-28 18:30:35,435] Trial 48 finished with value: 0.43148418664932253 and parameters: {'n_estimators': 949, 'learning_rate': 0.2744329489887136, 'max_depth': 7, 'min_child_weight': 2, 'gamma': 0.8837822072415009, 'subsample': 0.502146947802395, 'colsample_bytree': 0.8086645056135917, 'reg_alpha': 0.6606127328061231, 'reg_lambda': 9.96597973111648}. Best is trial 41 with value: 0.5458519577980041.
[I 2025-02-28 18:30:41,309] Trial 49 finished with value: 0.5215312957763671 and parameters: {'n_estimators': 802, 'learning_rate': 0.16891002755333676, 'max_depth': 4, 'min_child_weight': 3, 'gamma': 0.980728074563575, 'subsample': 0.5898947936728967, 'colsample_bytree': 0.6542891725895289, 'reg_alpha': 1.1067781204775877, 'reg_lambda': 7.9935035748966525}. Best is trial 41 with value: 0.5458519577980041.

Best trial: 41
Best R2 score: 0.5459
Best parameters: {'n_estimators': 403, 'learning_rate': 0.025181939608234893, 'max_depth': 4, 'min_child_weight': 2, 'gamma': 0.9450617049891935, 'subsample': 0.6775014498470824, 'colsample_bytree': 0.7494749285293014, 'reg_alpha': 1.605804505030021, 'reg_lambda': 8.650350883129157}

XGBRegressor(base_score=None, booster=None, callbacks=None,
             colsample_bylevel=None, colsample_bynode=None,
             colsample_bytree=0.7494749285293014, device=None,
             early_stopping_rounds=None, enable_categorical=False,
             eval_metric=None, feature_types=None, gamma=0.9450617049891935,
             grow_policy=None, importance_type=None,
             interaction_constraints=None, learning_rate=0.025181939608234893,
             max_bin=None, max_cat_threshold=None, max_cat_to_onehot=None,
             max_delta_step=None, max_depth=4, max_leaves=None,
             min_child_weight=2, missing=nan, monotone_constraints=None,
             multi_strategy=None, n_estimators=403, n_jobs=None,
             num_parallel_tree=None, random_state=None, ...)

XGBRegressor(base_score=None, booster=None, callbacks=None,
             colsample_bylevel=None, colsample_bynode=None,
             colsample_bytree=0.7494749285293014, device=None,
             early_stopping_rounds=None, enable_categorical=False,
             eval_metric=None, feature_types=None, gamma=0.9450617049891935,
             grow_policy=None, importance_type=None,
             interaction_constraints=None, learning_rate=0.025181939608234893,
             max_bin=None, max_cat_threshold=None, max_cat_to_onehot=None,
             max_delta_step=None, max_depth=4, max_leaves=None,
             min_child_weight=2, missing=nan, monotone_constraints=None,
             multi_strategy=None, n_estimators=403, n_jobs=None,
             num_parallel_tree=None, random_state=None, ...)

tune_with_optuna('lightgbm')

[I 2025-02-28 18:33:22,410] A new study created in memory with name: no-name-907c1fb3-8399-4bed-bbc6-3b54147e7028

Tuning lightgbm with Optuna...

[I 2025-02-28 18:33:27,720] Trial 0 finished with value: 0.5326662266336206 and parameters: {'n_estimators': 629, 'learning_rate': 0.19440969104676345, 'max_depth': 6, 'num_leaves': 75, 'min_child_samples': 85, 'subsample': 0.6848108451598178, 'colsample_bytree': 0.5040101283257208, 'reg_alpha': 1.494238109285655, 'reg_lambda': 2.8567483167100804}. Best is trial 0 with value: 0.5326662266336206.
[I 2025-02-28 18:33:28,178] Trial 1 finished with value: 0.5410214784890865 and parameters: {'n_estimators': 150, 'learning_rate': 0.14099869668804374, 'max_depth': 4, 'num_leaves': 79, 'min_child_samples': 36, 'subsample': 0.8130008038302748, 'colsample_bytree': 0.7693373361439555, 'reg_alpha': 6.305577356850068, 'reg_lambda': 4.232341972652249}. Best is trial 1 with value: 0.5410214784890865.
[I 2025-02-28 18:33:31,569] Trial 2 finished with value: 0.5377573182053613 and parameters: {'n_estimators': 779, 'learning_rate': 0.07472664147668032, 'max_depth': 4, 'num_leaves': 155, 'min_child_samples': 42, 'subsample': 0.9709402817685133, 'colsample_bytree': 0.7252879942027699, 'reg_alpha': 8.54104157618054, 'reg_lambda': 6.190736802834839}. Best is trial 1 with value: 0.5410214784890865.
[I 2025-02-28 18:33:35,420] Trial 3 finished with value: 0.5303618511898678 and parameters: {'n_estimators': 659, 'learning_rate': 0.11377300036644683, 'max_depth': 10, 'num_leaves': 90, 'min_child_samples': 98, 'subsample': 0.67708965639584, 'colsample_bytree': 0.6419376081350582, 'reg_alpha': 1.5040045119179457, 'reg_lambda': 6.837348145437019}. Best is trial 1 with value: 0.5410214784890865.
[I 2025-02-28 18:33:36,115] Trial 4 finished with value: 0.5378743214204842 and parameters: {'n_estimators': 309, 'learning_rate': 0.17421406214155305, 'max_depth': 3, 'num_leaves': 113, 'min_child_samples': 34, 'subsample': 0.9738099891070344, 'colsample_bytree': 0.7562528414871743, 'reg_alpha': 5.133529252218217, 'reg_lambda': 2.11155294172321}. Best is trial 1 with value: 0.5410214784890865.
[I 2025-02-28 18:33:39,233] Trial 5 finished with value: 0.5215350745032434 and parameters: {'n_estimators': 341, 'learning_rate': 0.18767238417574686, 'max_depth': 10, 'num_leaves': 136, 'min_child_samples': 66, 'subsample': 0.8867151507232669, 'colsample_bytree': 0.9092772966637461, 'reg_alpha': 6.138544864189051, 'reg_lambda': 6.242063310000051}. Best is trial 1 with value: 0.5410214784890865.
[I 2025-02-28 18:33:42,612] Trial 6 finished with value: 0.5417250030856776 and parameters: {'n_estimators': 502, 'learning_rate': 0.029940907936526262, 'max_depth': 5, 'num_leaves': 112, 'min_child_samples': 37, 'subsample': 0.8965774632044667, 'colsample_bytree': 0.706188547974648, 'reg_alpha': 9.858552429397744, 'reg_lambda': 6.876734019667184}. Best is trial 6 with value: 0.5417250030856776.
[I 2025-02-28 18:33:47,924] Trial 7 finished with value: 0.5215763778434364 and parameters: {'n_estimators': 796, 'learning_rate': 0.12560450508861962, 'max_depth': 6, 'num_leaves': 42, 'min_child_samples': 21, 'subsample': 0.6066766343884689, 'colsample_bytree': 0.6659956073752201, 'reg_alpha': 5.889095924211835, 'reg_lambda': 5.0554002307174954}. Best is trial 6 with value: 0.5417250030856776.
[I 2025-02-28 18:33:52,614] Trial 8 finished with value: 0.5092863005557293 and parameters: {'n_estimators': 977, 'learning_rate': 0.27120086458914267, 'max_depth': 8, 'num_leaves': 29, 'min_child_samples': 79, 'subsample': 0.9243835981489068, 'colsample_bytree': 0.7532166091964823, 'reg_alpha': 8.9896729330966, 'reg_lambda': 5.630390304010492}. Best is trial 6 with value: 0.5417250030856776.
[I 2025-02-28 18:33:56,688] Trial 9 finished with value: 0.5025441274070831 and parameters: {'n_estimators': 728, 'learning_rate': 0.2917512797636476, 'max_depth': 9, 'num_leaves': 150, 'min_child_samples': 28, 'subsample': 0.6336649862655541, 'colsample_bytree': 0.5572172130464979, 'reg_alpha': 5.527068948583429, 'reg_lambda': 7.285684249055668}. Best is trial 6 with value: 0.5417250030856776.
[I 2025-02-28 18:33:59,809] Trial 10 finished with value: 0.5397143085926579 and parameters: {'n_estimators': 394, 'learning_rate': 0.023293553559949526, 'max_depth': 7, 'num_leaves': 195, 'min_child_samples': 9, 'subsample': 0.7886885096146093, 'colsample_bytree': 0.8865561891282174, 'reg_alpha': 9.37212168472918, 'reg_lambda': 9.180762799566521}. Best is trial 6 with value: 0.5417250030856776.
[I 2025-02-28 18:34:00,543] Trial 11 finished with value: 0.5440497774562261 and parameters: {'n_estimators': 169, 'learning_rate': 0.0575100237763993, 'max_depth': 4, 'num_leaves': 65, 'min_child_samples': 53, 'subsample': 0.806500640439573, 'colsample_bytree': 0.8368286546246911, 'reg_alpha': 7.5362380941522025, 'reg_lambda': 3.7573596446273814}. Best is trial 11 with value: 0.5440497774562261.
[I 2025-02-28 18:34:01,227] Trial 12 finished with value: 0.5246318104414452 and parameters: {'n_estimators': 104, 'learning_rate': 0.020000160544995246, 'max_depth': 5, 'num_leaves': 46, 'min_child_samples': 52, 'subsample': 0.514173455947583, 'colsample_bytree': 0.9982699830405768, 'reg_alpha': 7.371816306408743, 'reg_lambda': 0.29518524208796215}. Best is trial 11 with value: 0.5440497774562261.
[I 2025-02-28 18:34:02,712] Trial 13 finished with value: 0.5411925234210939 and parameters: {'n_estimators': 463, 'learning_rate': 0.0764391252126574, 'max_depth': 3, 'num_leaves': 105, 'min_child_samples': 58, 'subsample': 0.8589779586148867, 'colsample_bytree': 0.8593960774380958, 'reg_alpha': 3.349327734980789, 'reg_lambda': 8.825646631511722}. Best is trial 11 with value: 0.5440497774562261.
[I 2025-02-28 18:34:03,766] Trial 14 finished with value: 0.5404643214473739 and parameters: {'n_estimators': 232, 'learning_rate': 0.07265748179368517, 'max_depth': 5, 'num_leaves': 65, 'min_child_samples': 52, 'subsample': 0.7541433203124146, 'colsample_bytree': 0.8225882980665425, 'reg_alpha': 7.808907338965442, 'reg_lambda': 3.893214122646761}. Best is trial 11 with value: 0.5440497774562261.
[I 2025-02-28 18:34:06,271] Trial 15 finished with value: 0.5414486987170964 and parameters: {'n_estimators': 500, 'learning_rate': 0.03921614899461118, 'max_depth': 5, 'num_leaves': 119, 'min_child_samples': 68, 'subsample': 0.8487149098935276, 'colsample_bytree': 0.6525639278829782, 'reg_alpha': 9.854851648190847, 'reg_lambda': 8.237653827910606}. Best is trial 11 with value: 0.5440497774562261.
[I 2025-02-28 18:34:07,070] Trial 16 finished with value: 0.5443086205520119 and parameters: {'n_estimators': 260, 'learning_rate': 0.05354527857411969, 'max_depth': 4, 'num_leaves': 181, 'min_child_samples': 14, 'subsample': 0.9034527304964098, 'colsample_bytree': 0.9994159970452017, 'reg_alpha': 7.570311497851004, 'reg_lambda': 1.3405041995581706}. Best is trial 16 with value: 0.5443086205520119.
[I 2025-02-28 18:34:07,759] Trial 17 finished with value: 0.5295824853867158 and parameters: {'n_estimators': 228, 'learning_rate': 0.22438058810292544, 'max_depth': 4, 'num_leaves': 170, 'min_child_samples': 12, 'subsample': 0.7304901298156259, 'colsample_bytree': 0.9983176321159564, 'reg_alpha': 3.5530664186589047, 'reg_lambda': 0.3217559236443166}. Best is trial 16 with value: 0.5443086205520119.
[I 2025-02-28 18:34:08,327] Trial 18 finished with value: 0.542659887557329 and parameters: {'n_estimators': 227, 'learning_rate': 0.1074330533270406, 'max_depth': 3, 'num_leaves': 200, 'min_child_samples': 5, 'subsample': 0.8127746284476145, 'colsample_bytree': 0.9166221827780916, 'reg_alpha': 7.493120614100051, 'reg_lambda': 1.6881099685242342}. Best is trial 16 with value: 0.5443086205520119.
[I 2025-02-28 18:34:10,478] Trial 19 finished with value: 0.5314217033148203 and parameters: {'n_estimators': 380, 'learning_rate': 0.08711656962220418, 'max_depth': 7, 'num_leaves': 171, 'min_child_samples': 46, 'subsample': 0.9970050654981224, 'colsample_bytree': 0.9489513574602209, 'reg_alpha': 3.9791562588878326, 'reg_lambda': 3.3760319121733873}. Best is trial 16 with value: 0.5443086205520119.
[I 2025-02-28 18:34:11,014] Trial 20 finished with value: 0.5450057029343796 and parameters: {'n_estimators': 160, 'learning_rate': 0.06003691234250976, 'max_depth': 4, 'num_leaves': 58, 'min_child_samples': 22, 'subsample': 0.9435407081247855, 'colsample_bytree': 0.817209088334033, 'reg_alpha': 0.008716293076002302, 'reg_lambda': 1.6787101201614192}. Best is trial 20 with value: 0.5450057029343796.
[I 2025-02-28 18:34:13,453] Trial 21 finished with value: 0.5445812148281128 and parameters: {'n_estimators': 178, 'learning_rate': 0.051386159440118845, 'max_depth': 4, 'num_leaves': 57, 'min_child_samples': 23, 'subsample': 0.9217250689320882, 'colsample_bytree': 0.820165779592411, 'reg_alpha': 0.12838244355625866, 'reg_lambda': 1.7191303037263683}. Best is trial 20 with value: 0.5450057029343796.
[I 2025-02-28 18:34:19,634] Trial 22 finished with value: 0.5425661132752796 and parameters: {'n_estimators': 290, 'learning_rate': 0.04511697178277499, 'max_depth': 3, 'num_leaves': 21, 'min_child_samples': 19, 'subsample': 0.9267869847901363, 'colsample_bytree': 0.7994204834613143, 'reg_alpha': 0.038883105269208976, 'reg_lambda': 1.3753824302594748}. Best is trial 20 with value: 0.5450057029343796.
[I 2025-02-28 18:34:20,065] Trial 23 finished with value: 0.5456215903300075 and parameters: {'n_estimators': 105, 'learning_rate': 0.08836732558896855, 'max_depth': 4, 'num_leaves': 45, 'min_child_samples': 21, 'subsample': 0.9333867867274527, 'colsample_bytree': 0.9562564045513104, 'reg_alpha': 0.4431230557718911, 'reg_lambda': 1.0592541089500838}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:20,890] Trial 24 finished with value: 0.5405766869803859 and parameters: {'n_estimators': 112, 'learning_rate': 0.08746086685679198, 'max_depth': 6, 'num_leaves': 46, 'min_child_samples': 27, 'subsample': 0.9520788371967963, 'colsample_bytree': 0.9440650557990548, 'reg_alpha': 0.046171908853950505, 'reg_lambda': 2.244366121149166}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:21,918] Trial 25 finished with value: 0.535510589956807 and parameters: {'n_estimators': 199, 'learning_rate': 0.14901860687126928, 'max_depth': 5, 'num_leaves': 61, 'min_child_samples': 25, 'subsample': 0.8674362826129792, 'colsample_bytree': 0.8644110156075968, 'reg_alpha': 1.3753040510819154, 'reg_lambda': 0.13728504436942557}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:23,554] Trial 26 finished with value: 0.49995194757989825 and parameters: {'n_estimators': 160, 'learning_rate': 0.011295858507771685, 'max_depth': 4, 'num_leaves': 33, 'min_child_samples': 19, 'subsample': 0.9299751072228464, 'colsample_bytree': 0.7995893745529109, 'reg_alpha': 0.8271453383923701, 'reg_lambda': 0.9031907867979468}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:24,618] Trial 27 finished with value: 0.54136394751594 and parameters: {'n_estimators': 323, 'learning_rate': 0.09626595448073069, 'max_depth': 3, 'num_leaves': 88, 'min_child_samples': 30, 'subsample': 0.9938516134243033, 'colsample_bytree': 0.7976554971033438, 'reg_alpha': 2.405818067427746, 'reg_lambda': 2.5967127499683675}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:26,927] Trial 28 finished with value: 0.5201181333296389 and parameters: {'n_estimators': 427, 'learning_rate': 0.13194627344054186, 'max_depth': 6, 'num_leaves': 54, 'min_child_samples': 19, 'subsample': 0.9519086905723467, 'colsample_bytree': 0.9601844464005312, 'reg_alpha': 2.4385442493846776, 'reg_lambda': 3.045706229465728}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:31,801] Trial 29 finished with value: 0.4915880380404 and parameters: {'n_estimators': 600, 'learning_rate': 0.2163074058331411, 'max_depth': 6, 'num_leaves': 77, 'min_child_samples': 5, 'subsample': 0.8404272741760088, 'colsample_bytree': 0.5791174303702202, 'reg_alpha': 0.763131541151066, 'reg_lambda': 0.9138907938127938}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:32,783] Trial 30 finished with value: 0.5410774429353168 and parameters: {'n_estimators': 103, 'learning_rate': 0.05767722540963362, 'max_depth': 7, 'num_leaves': 96, 'min_child_samples': 42, 'subsample': 0.7550155301064561, 'colsample_bytree': 0.8841437378831947, 'reg_alpha': 1.823241040317661, 'reg_lambda': 4.8248189525894345}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:33,878] Trial 31 finished with value: 0.5447656530021804 and parameters: {'n_estimators': 254, 'learning_rate': 0.05808400877680589, 'max_depth': 4, 'num_leaves': 127, 'min_child_samples': 13, 'subsample': 0.8942519817661881, 'colsample_bytree': 0.9252226926952034, 'reg_alpha': 0.7700580765795652, 'reg_lambda': 1.3743962462567594}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:37,584] Trial 32 finished with value: 0.5429212425552031 and parameters: {'n_estimators': 174, 'learning_rate': 0.11050905579021411, 'max_depth': 4, 'num_leaves': 124, 'min_child_samples': 11, 'subsample': 0.88453908363, 'colsample_bytree': 0.911772275522064, 'reg_alpha': 0.5370022210437813, 'reg_lambda': 1.8440603852294066}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:39,240] Trial 33 finished with value: 0.5436706983035731 and parameters: {'n_estimators': 269, 'learning_rate': 0.06645477750923878, 'max_depth': 4, 'num_leaves': 72, 'min_child_samples': 23, 'subsample': 0.9529348589427186, 'colsample_bytree': 0.8425531247283318, 'reg_alpha': 2.1041811447376135, 'reg_lambda': 2.6945853442668843}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:39,925] Trial 34 finished with value: 0.5438783037552988 and parameters: {'n_estimators': 153, 'learning_rate': 0.037608832076791034, 'max_depth': 5, 'num_leaves': 134, 'min_child_samples': 15, 'subsample': 0.9169017549885521, 'colsample_bytree': 0.7105740579595161, 'reg_alpha': 1.1707672136006777, 'reg_lambda': 0.9705638843869945}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:40,428] Trial 35 finished with value: 0.5427154958498155 and parameters: {'n_estimators': 205, 'learning_rate': 0.08515035737680028, 'max_depth': 3, 'num_leaves': 99, 'min_child_samples': 35, 'subsample': 0.976577307146639, 'colsample_bytree': 0.9573780085655689, 'reg_alpha': 0.3574671209336951, 'reg_lambda': 2.097426660996745}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:41,574] Trial 36 finished with value: 0.5387107169068805 and parameters: {'n_estimators': 371, 'learning_rate': 0.10110259261973088, 'max_depth': 4, 'num_leaves': 88, 'min_child_samples': 30, 'subsample': 0.8374301871968041, 'colsample_bytree': 0.7818658554621556, 'reg_alpha': 1.0959483138214856, 'reg_lambda': 0.5995854012783639}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:43,202] Trial 37 finished with value: 0.5396968012491913 and parameters: {'n_estimators': 138, 'learning_rate': 0.12088174637805628, 'max_depth': 5, 'num_leaves': 56, 'min_child_samples': 41, 'subsample': 0.8796684297084698, 'colsample_bytree': 0.8863794724274013, 'reg_alpha': 2.9878992702263107, 'reg_lambda': 1.4572644846649254}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:43,869] Trial 38 finished with value: 0.5393594910745998 and parameters: {'n_estimators': 299, 'learning_rate': 0.17243087009432634, 'max_depth': 3, 'num_leaves': 39, 'min_child_samples': 16, 'subsample': 0.9594673375870353, 'colsample_bytree': 0.7432995022921125, 'reg_alpha': 4.1951285950019335, 'reg_lambda': 4.526524021636865}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:44,343] Trial 39 finished with value: 0.541503334093693 and parameters: {'n_estimators': 195, 'learning_rate': 0.04820279391746983, 'max_depth': 3, 'num_leaves': 23, 'min_child_samples': 34, 'subsample': 0.9089925422230793, 'colsample_bytree': 0.9157543526042334, 'reg_alpha': 1.6204116800140465, 'reg_lambda': 9.999165404425318}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:47,204] Trial 40 finished with value: 0.5402542217710835 and parameters: {'n_estimators': 891, 'learning_rate': 0.06386722099224824, 'max_depth': 4, 'num_leaves': 152, 'min_child_samples': 86, 'subsample': 0.9414246587526459, 'colsample_bytree': 0.8296867708818856, 'reg_alpha': 0.5138705769701981, 'reg_lambda': 2.9784502461790403}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:48,729] Trial 41 finished with value: 0.5445184518016682 and parameters: {'n_estimators': 265, 'learning_rate': 0.051112577038867596, 'max_depth': 4, 'num_leaves': 184, 'min_child_samples': 13, 'subsample': 0.8960916492228412, 'colsample_bytree': 0.9964304875925206, 'reg_alpha': 4.6547945352067925, 'reg_lambda': 1.0359297664635108}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:49,912] Trial 42 finished with value: 0.5442188536569572 and parameters: {'n_estimators': 258, 'learning_rate': 0.026715282361536048, 'max_depth': 4, 'num_leaves': 80, 'min_child_samples': 9, 'subsample': 0.8958234486894006, 'colsample_bytree': 0.9748527037126143, 'reg_alpha': 6.4933232426704475, 'reg_lambda': 0.037582154011755575}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:52,167] Trial 43 finished with value: 0.5427754113678465 and parameters: {'n_estimators': 340, 'learning_rate': 0.034722111409205815, 'max_depth': 5, 'num_leaves': 143, 'min_child_samples': 23, 'subsample': 0.9765221722257463, 'colsample_bytree': 0.9287061540163946, 'reg_alpha': 0.06984775689116524, 'reg_lambda': 2.399014779413541}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:53,066] Trial 44 finished with value: 0.49648814294248966 and parameters: {'n_estimators': 145, 'learning_rate': 0.01039799077016123, 'max_depth': 4, 'num_leaves': 51, 'min_child_samples': 17, 'subsample': 0.8667329383623265, 'colsample_bytree': 0.972684707238554, 'reg_alpha': 4.667484362671332, 'reg_lambda': 1.1404983522664032}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:54,907] Trial 45 finished with value: 0.5310781320211311 and parameters: {'n_estimators': 249, 'learning_rate': 0.07799566079346314, 'max_depth': 9, 'num_leaves': 35, 'min_child_samples': 7, 'subsample': 0.776795657756453, 'colsample_bytree': 0.8664037375368475, 'reg_alpha': 0.9866982748253421, 'reg_lambda': 1.9054159115405902}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:55,763] Trial 46 finished with value: 0.5444301348331371 and parameters: {'n_estimators': 191, 'learning_rate': 0.049908023287768236, 'max_depth': 4, 'num_leaves': 70, 'min_child_samples': 31, 'subsample': 0.7064742151056554, 'colsample_bytree': 0.9325350699218569, 'reg_alpha': 2.8681911029061515, 'reg_lambda': 0.6917947083432978}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:34:56,244] Trial 47 finished with value: 0.5389823110294107 and parameters: {'n_estimators': 100, 'learning_rate': 0.06892935443455488, 'max_depth': 3, 'num_leaves': 182, 'min_child_samples': 24, 'subsample': 0.8287928806960181, 'colsample_bytree': 0.6905499586878077, 'reg_alpha': 1.5501157097420872, 'reg_lambda': 1.6076542318068407}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:35:03,267] Trial 48 finished with value: 0.5292613035876131 and parameters: {'n_estimators': 659, 'learning_rate': 0.09668139637933358, 'max_depth': 5, 'num_leaves': 129, 'min_child_samples': 38, 'subsample': 0.6361764555366813, 'colsample_bytree': 0.9699246977527767, 'reg_alpha': 1.9624990748351678, 'reg_lambda': 3.4702833737538317}. Best is trial 23 with value: 0.5456215903300075.
[I 2025-02-28 18:35:05,061] Trial 49 finished with value: 0.525258471414587 and parameters: {'n_estimators': 298, 'learning_rate': 0.1327156660852742, 'max_depth': 6, 'num_leaves': 158, 'min_child_samples': 12, 'subsample': 0.9313406143953251, 'colsample_bytree': 0.8903897279513846, 'reg_alpha': 6.816620129550619, 'reg_lambda': 5.469460667657804}. Best is trial 23 with value: 0.5456215903300075.

Best trial: 23
Best R2 score: 0.5456
Best parameters: {'n_estimators': 105, 'learning_rate': 0.08836732558896855, 'max_depth': 4, 'num_leaves': 45, 'min_child_samples': 21, 'subsample': 0.9333867867274527, 'colsample_bytree': 0.9562564045513104, 'reg_alpha': 0.4431230557718911, 'reg_lambda': 1.0592541089500838}

LGBMRegressor(colsample_bytree=0.9562564045513104,
              learning_rate=0.08836732558896855, max_depth=4,
              min_child_samples=21, n_estimators=105, num_leaves=45,
              reg_alpha=0.4431230557718911, reg_lambda=1.0592541089500838,
              subsample=0.9333867867274527)

LGBMRegressor(colsample_bytree=0.9562564045513104,
              learning_rate=0.08836732558896855, max_depth=4,
              min_child_samples=21, n_estimators=105, num_leaves=45,
              reg_alpha=0.4431230557718911, reg_lambda=1.0592541089500838,
              subsample=0.9333867867274527)

tune_with_optuna('gbr')

[I 2025-02-28 18:37:07,435] A new study created in memory with name: no-name-bff5797b-c4c7-420e-8423-0eb272ac4979

Tuning gbr with Optuna...

[I 2025-02-28 18:37:17,518] Trial 0 finished with value: 0.5166258331501118 and parameters: {'n_estimators': 371, 'learning_rate': 0.23149802485829724, 'max_depth': 5, 'min_samples_split': 8, 'min_samples_leaf': 6, 'subsample': 0.8654801770757944, 'max_features': 'sqrt'}. Best is trial 0 with value: 0.5166258331501118.
[I 2025-02-28 18:37:31,525] Trial 1 finished with value: 0.5011830303200927 and parameters: {'n_estimators': 597, 'learning_rate': 0.16297507958502855, 'max_depth': 6, 'min_samples_split': 16, 'min_samples_leaf': 5, 'subsample': 0.9385872347320672, 'max_features': 'sqrt'}. Best is trial 0 with value: 0.5166258331501118.
[I 2025-02-28 18:37:49,758] Trial 2 finished with value: 0.46754387432227185 and parameters: {'n_estimators': 581, 'learning_rate': 0.13266622970545963, 'max_depth': 8, 'min_samples_split': 15, 'min_samples_leaf': 3, 'subsample': 0.8769286659977769, 'max_features': 'log2'}. Best is trial 0 with value: 0.5166258331501118.
[I 2025-02-28 18:37:59,836] Trial 3 finished with value: 0.48447491534964604 and parameters: {'n_estimators': 258, 'learning_rate': 0.21758901231806224, 'max_depth': 9, 'min_samples_split': 17, 'min_samples_leaf': 6, 'subsample': 0.6567767542664944, 'max_features': 'log2'}. Best is trial 0 with value: 0.5166258331501118.
[I 2025-02-28 18:38:33,678] Trial 4 finished with value: 0.48657479842045426 and parameters: {'n_estimators': 694, 'learning_rate': 0.14420086005981206, 'max_depth': 7, 'min_samples_split': 11, 'min_samples_leaf': 6, 'subsample': 0.6442223861292229, 'max_features': 'log2'}. Best is trial 0 with value: 0.5166258331501118.
[I 2025-02-28 18:38:51,121] Trial 5 finished with value: 0.513709258108584 and parameters: {'n_estimators': 729, 'learning_rate': 0.1880798784796406, 'max_depth': 5, 'min_samples_split': 3, 'min_samples_leaf': 10, 'subsample': 0.7923205103911215, 'max_features': 'sqrt'}. Best is trial 0 with value: 0.5166258331501118.
[I 2025-02-28 18:39:05,886] Trial 6 finished with value: 0.39744537459852963 and parameters: {'n_estimators': 482, 'learning_rate': 0.2874701249273012, 'max_depth': 10, 'min_samples_split': 9, 'min_samples_leaf': 4, 'subsample': 0.8650893517864041, 'max_features': 'log2'}. Best is trial 0 with value: 0.5166258331501118.
[I 2025-02-28 18:39:09,982] Trial 7 finished with value: 0.5275963120649791 and parameters: {'n_estimators': 173, 'learning_rate': 0.15440197329999186, 'max_depth': 6, 'min_samples_split': 15, 'min_samples_leaf': 2, 'subsample': 0.9524441160270005, 'max_features': 'sqrt'}. Best is trial 7 with value: 0.5275963120649791.
[I 2025-02-28 18:39:30,982] Trial 8 finished with value: 0.4447553338956525 and parameters: {'n_estimators': 772, 'learning_rate': 0.14481270830876722, 'max_depth': 9, 'min_samples_split': 2, 'min_samples_leaf': 5, 'subsample': 0.8492243714089422, 'max_features': 'sqrt'}. Best is trial 7 with value: 0.5275963120649791.
[I 2025-02-28 18:39:50,694] Trial 9 finished with value: 0.5009965748591971 and parameters: {'n_estimators': 904, 'learning_rate': 0.09770195111574961, 'max_depth': 6, 'min_samples_split': 2, 'min_samples_leaf': 4, 'subsample': 0.845242795990188, 'max_features': 'sqrt'}. Best is trial 7 with value: 0.5275963120649791.
[I 2025-02-28 18:39:54,616] Trial 10 finished with value: 0.4856570793039988 and parameters: {'n_estimators': 100, 'learning_rate': 0.0158195981360717, 'max_depth': 3, 'min_samples_split': 20, 'min_samples_leaf': 1, 'subsample': 0.5534182536566528, 'max_features': None}. Best is trial 7 with value: 0.5275963120649791.
[I 2025-02-28 18:40:00,484] Trial 11 finished with value: 0.5322821113025176 and parameters: {'n_estimators': 249, 'learning_rate': 0.24880540941081658, 'max_depth': 4, 'min_samples_split': 7, 'min_samples_leaf': 8, 'subsample': 0.9793200911044663, 'max_features': 'sqrt'}. Best is trial 11 with value: 0.5322821113025176.
[I 2025-02-28 18:40:06,964] Trial 12 finished with value: 0.5341450618057997 and parameters: {'n_estimators': 143, 'learning_rate': 0.2841875556141446, 'max_depth': 3, 'min_samples_split': 6, 'min_samples_leaf': 9, 'subsample': 0.9978996570520571, 'max_features': None}. Best is trial 12 with value: 0.5341450618057997.
[I 2025-02-28 18:40:21,958] Trial 13 finished with value: 0.5191535779959852 and parameters: {'n_estimators': 313, 'learning_rate': 0.2993437119857678, 'max_depth': 3, 'min_samples_split': 6, 'min_samples_leaf': 9, 'subsample': 0.9944523744088988, 'max_features': None}. Best is trial 12 with value: 0.5341450618057997.
[I 2025-02-28 18:40:37,685] Trial 14 finished with value: 0.5056679911090216 and parameters: {'n_estimators': 418, 'learning_rate': 0.2471412387561913, 'max_depth': 4, 'min_samples_split': 6, 'min_samples_leaf': 8, 'subsample': 0.9982987291810923, 'max_features': None}. Best is trial 12 with value: 0.5341450618057997.
[I 2025-02-28 18:40:45,036] Trial 15 finished with value: 0.5092445560008925 and parameters: {'n_estimators': 245, 'learning_rate': 0.2639713069965241, 'max_depth': 4, 'min_samples_split': 5, 'min_samples_leaf': 8, 'subsample': 0.7141662972999565, 'max_features': None}. Best is trial 12 with value: 0.5341450618057997.
[I 2025-02-28 18:40:52,710] Trial 16 finished with value: 0.5267751128450314 and parameters: {'n_estimators': 184, 'learning_rate': 0.2084217747264252, 'max_depth': 4, 'min_samples_split': 11, 'min_samples_leaf': 8, 'subsample': 0.9252964221661318, 'max_features': None}. Best is trial 12 with value: 0.5341450618057997.
[I 2025-02-28 18:40:56,885] Trial 17 finished with value: 0.5376825710642157 and parameters: {'n_estimators': 106, 'learning_rate': 0.2671548773506419, 'max_depth': 3, 'min_samples_split': 8, 'min_samples_leaf': 10, 'subsample': 0.7880943235243648, 'max_features': None}. Best is trial 17 with value: 0.5376825710642157.
[I 2025-02-28 18:41:00,748] Trial 18 finished with value: 0.5416257967246378 and parameters: {'n_estimators': 123, 'learning_rate': 0.09423480329576486, 'max_depth': 3, 'min_samples_split': 9, 'min_samples_leaf': 10, 'subsample': 0.512923259349313, 'max_features': None}. Best is trial 18 with value: 0.5416257967246378.
[I 2025-02-28 18:41:13,212] Trial 19 finished with value: 0.5208678147341531 and parameters: {'n_estimators': 462, 'learning_rate': 0.07019810766489495, 'max_depth': 5, 'min_samples_split': 10, 'min_samples_leaf': 10, 'subsample': 0.5168346995942698, 'max_features': None}. Best is trial 18 with value: 0.5416257967246378.
[I 2025-02-28 18:41:22,515] Trial 20 finished with value: 0.5416957030088807 and parameters: {'n_estimators': 361, 'learning_rate': 0.07369596953659807, 'max_depth': 3, 'min_samples_split': 13, 'min_samples_leaf': 10, 'subsample': 0.7440250200014602, 'max_features': None}. Best is trial 20 with value: 0.5416957030088807.
[I 2025-02-28 18:41:33,415] Trial 21 finished with value: 0.5426331486901319 and parameters: {'n_estimators': 338, 'learning_rate': 0.06477196411506755, 'max_depth': 3, 'min_samples_split': 13, 'min_samples_leaf': 10, 'subsample': 0.7787886752931414, 'max_features': None}. Best is trial 21 with value: 0.5426331486901319.
[I 2025-02-28 18:41:44,917] Trial 22 finished with value: 0.5428936591876395 and parameters: {'n_estimators': 347, 'learning_rate': 0.06064214039077384, 'max_depth': 3, 'min_samples_split': 12, 'min_samples_leaf': 9, 'subsample': 0.7127842938125919, 'max_features': None}. Best is trial 22 with value: 0.5428936591876395.
[I 2025-02-28 18:42:03,260] Trial 23 finished with value: 0.543469553667053 and parameters: {'n_estimators': 353, 'learning_rate': 0.039199470874611626, 'max_depth': 4, 'min_samples_split': 14, 'min_samples_leaf': 9, 'subsample': 0.739062694687006, 'max_features': None}. Best is trial 23 with value: 0.543469553667053.
[I 2025-02-28 18:42:21,265] Trial 24 finished with value: 0.5457570109135942 and parameters: {'n_estimators': 532, 'learning_rate': 0.013201142547601463, 'max_depth': 4, 'min_samples_split': 13, 'min_samples_leaf': 7, 'subsample': 0.6777821390980873, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:42:42,385] Trial 25 finished with value: 0.5439261216932461 and parameters: {'n_estimators': 532, 'learning_rate': 0.010039986736273668, 'max_depth': 5, 'min_samples_split': 13, 'min_samples_leaf': 7, 'subsample': 0.6498643321838303, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:43:01,640] Trial 26 finished with value: 0.5436549026412915 and parameters: {'n_estimators': 527, 'learning_rate': 0.012657542037501569, 'max_depth': 5, 'min_samples_split': 18, 'min_samples_leaf': 7, 'subsample': 0.632831158101171, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:43:39,045] Trial 27 finished with value: 0.5436108167392069 and parameters: {'n_estimators': 648, 'learning_rate': 0.010479491492067202, 'max_depth': 5, 'min_samples_split': 19, 'min_samples_leaf': 7, 'subsample': 0.6263160862609665, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:44:17,342] Trial 28 finished with value: 0.5188927330135028 and parameters: {'n_estimators': 526, 'learning_rate': 0.03144435154272926, 'max_depth': 7, 'min_samples_split': 18, 'min_samples_leaf': 7, 'subsample': 0.6064182077680091, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:44:50,139] Trial 29 finished with value: 0.5318818151914331 and parameters: {'n_estimators': 528, 'learning_rate': 0.037078760979773806, 'max_depth': 5, 'min_samples_split': 17, 'min_samples_leaf': 7, 'subsample': 0.6793627926448832, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:45:17,226] Trial 30 finished with value: 0.5200594442228811 and parameters: {'n_estimators': 828, 'learning_rate': 0.10160343797110957, 'max_depth': 5, 'min_samples_split': 14, 'min_samples_leaf': 6, 'subsample': 0.5913224517175929, 'max_features': 'log2'}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:45:46,037] Trial 31 finished with value: 0.5437248279671836 and parameters: {'n_estimators': 642, 'learning_rate': 0.010718707706394888, 'max_depth': 5, 'min_samples_split': 20, 'min_samples_leaf': 7, 'subsample': 0.6192044818969257, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:46:20,067] Trial 32 finished with value: 0.5279056342257883 and parameters: {'n_estimators': 648, 'learning_rate': 0.024977632144370873, 'max_depth': 6, 'min_samples_split': 20, 'min_samples_leaf': 7, 'subsample': 0.5747001517631624, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:46:40,594] Trial 33 finished with value: 0.521898238645211 and parameters: {'n_estimators': 562, 'learning_rate': 0.053136898230836574, 'max_depth': 5, 'min_samples_split': 18, 'min_samples_leaf': 5, 'subsample': 0.6810347705111421, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:47:22,430] Trial 34 finished with value: 0.5012564856508492 and parameters: {'n_estimators': 616, 'learning_rate': 0.044852191212167415, 'max_depth': 7, 'min_samples_split': 16, 'min_samples_leaf': 6, 'subsample': 0.5526377301388273, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:47:45,550] Trial 35 finished with value: 0.5404149482117955 and parameters: {'n_estimators': 480, 'learning_rate': 0.012788846087546015, 'max_depth': 6, 'min_samples_split': 16, 'min_samples_leaf': 7, 'subsample': 0.6614972336753118, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:47:52,161] Trial 36 finished with value: 0.5356853105269188 and parameters: {'n_estimators': 421, 'learning_rate': 0.11546072593103919, 'max_depth': 4, 'min_samples_split': 19, 'min_samples_leaf': 5, 'subsample': 0.6306622817556439, 'max_features': 'log2'}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:48:27,370] Trial 37 finished with value: 0.5238012786375147 and parameters: {'n_estimators': 703, 'learning_rate': 0.027445701082624965, 'max_depth': 6, 'min_samples_split': 17, 'min_samples_leaf': 6, 'subsample': 0.7075722781366109, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:48:54,141] Trial 38 finished with value: 0.4803893172806074 and parameters: {'n_estimators': 585, 'learning_rate': 0.08241134882850128, 'max_depth': 7, 'min_samples_split': 15, 'min_samples_leaf': 7, 'subsample': 0.6158320947239292, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:49:12,312] Trial 39 finished with value: 0.5191469540618101 and parameters: {'n_estimators': 765, 'learning_rate': 0.04867681569444588, 'max_depth': 8, 'min_samples_split': 19, 'min_samples_leaf': 8, 'subsample': 0.6556495911466975, 'max_features': 'log2'}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:49:27,121] Trial 40 finished with value: 0.51445861942503 and parameters: {'n_estimators': 996, 'learning_rate': 0.17604560515527518, 'max_depth': 4, 'min_samples_split': 12, 'min_samples_leaf': 5, 'subsample': 0.6865704822754182, 'max_features': 'sqrt'}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:49:49,832] Trial 41 finished with value: 0.5428321400737083 and parameters: {'n_estimators': 656, 'learning_rate': 0.012314841065014846, 'max_depth': 5, 'min_samples_split': 19, 'min_samples_leaf': 7, 'subsample': 0.6321577435982716, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:50:16,816] Trial 42 finished with value: 0.5429624565039538 and parameters: {'n_estimators': 630, 'learning_rate': 0.012421853867381209, 'max_depth': 5, 'min_samples_split': 20, 'min_samples_leaf': 6, 'subsample': 0.5769075212947131, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:50:40,490] Trial 43 finished with value: 0.5305765917532641 and parameters: {'n_estimators': 532, 'learning_rate': 0.025803873387967642, 'max_depth': 6, 'min_samples_split': 18, 'min_samples_leaf': 7, 'subsample': 0.6127969490955832, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:51:07,869] Trial 44 finished with value: 0.5169077552483072 and parameters: {'n_estimators': 664, 'learning_rate': 0.05177198947130677, 'max_depth': 5, 'min_samples_split': 16, 'min_samples_leaf': 4, 'subsample': 0.6490376456361933, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:51:17,510] Trial 45 finished with value: 0.5335218764322195 and parameters: {'n_estimators': 439, 'learning_rate': 0.010319344258733786, 'max_depth': 4, 'min_samples_split': 19, 'min_samples_leaf': 6, 'subsample': 0.5415114067883431, 'max_features': 'sqrt'}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:51:36,072] Trial 46 finished with value: 0.5419270218451692 and parameters: {'n_estimators': 576, 'learning_rate': 0.028425282082328862, 'max_depth': 5, 'min_samples_split': 14, 'min_samples_leaf': 8, 'subsample': 0.5953717473890078, 'max_features': 'log2'}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:52:16,879] Trial 47 finished with value: 0.5161883235424825 and parameters: {'n_estimators': 720, 'learning_rate': 0.037834002926623006, 'max_depth': 6, 'min_samples_split': 17, 'min_samples_leaf': 8, 'subsample': 0.6315956912901397, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:52:42,653] Trial 48 finished with value: 0.5399822816152737 and parameters: {'n_estimators': 515, 'learning_rate': 0.021419953513921924, 'max_depth': 5, 'min_samples_split': 20, 'min_samples_leaf': 6, 'subsample': 0.6687823840080587, 'max_features': None}. Best is trial 24 with value: 0.5457570109135942.
[I 2025-02-28 18:53:18,400] Trial 49 finished with value: 0.4661191543056004 and parameters: {'n_estimators': 750, 'learning_rate': 0.12102882067315053, 'max_depth': 10, 'min_samples_split': 18, 'min_samples_leaf': 7, 'subsample': 0.704352712615413, 'max_features': 'sqrt'}. Best is trial 24 with value: 0.5457570109135942.

Best trial: 24
Best R2 score: 0.5458
Best parameters: {'n_estimators': 532, 'learning_rate': 0.013201142547601463, 'max_depth': 4, 'min_samples_split': 13, 'min_samples_leaf': 7, 'subsample': 0.6777821390980873, 'max_features': None}

GradientBoostingRegressor(learning_rate=0.013201142547601463, max_depth=4,
                          min_samples_leaf=7, min_samples_split=13,
                          n_estimators=532, subsample=0.6777821390980873)

GradientBoostingRegressor(learning_rate=0.013201142547601463, max_depth=4,
                          min_samples_leaf=7, min_samples_split=13,
                          n_estimators=532, subsample=0.6777821390980873)

# Define a dictionary of regression models
regression_models_3 = {
    "GradientBoosting_Tuned_2": GradientBoostingRegressor(min_samples_leaf=4, min_samples_split=10,random_state=42, subsample=0.8),
    "XGBoost_Tuned_2": xgb.XGBRegressor(base_score=None, booster=None, callbacks=None, colsample_bylevel=None, colsample_bynode=None, colsample_bytree=1.0, device=None, early_stopping_rounds=None,enable_categorical=False, eval_metric=None, feature_types=None, gamma=0.2, grow_policy=None, importance_type=None, interaction_constraints=None, learning_rate=0.05, max_bin=None, max_cat_threshold=None, max_cat_to_onehot=None,max_delta_step=None, max_depth=3, max_leaves=None,min_child_weight=3, monotone_constraints=None,multi_strategy=None, n_estimators=500, n_jobs=None,num_parallel_tree=None, random_state=42),
    "LightGBM_Tuned_2": lgb.LGBMRegressor(colsample_bytree=0.6, learning_rate=0.05, max_depth=3,min_child_samples=5, n_estimators=500, num_leaves=50,random_state=42, reg_alpha=10, reg_lambda=1, subsample=0.6,verbose=-1),
    "GradientBoosting_Optima": GradientBoostingRegressor(learning_rate=0.013201142547601463, max_depth=4,min_samples_leaf=7, min_samples_split=13,n_estimators=532, subsample=0.6777821390980873),
    "XGBoost_Tuned_Optima": xgb.XGBRegressor(base_score=None, booster=None, callbacks=None,colsample_bylevel=None, colsample_bynode=None,colsample_bytree=0.7494749285293014, device=None,early_stopping_rounds=None, enable_categorical=False,eval_metric=None, feature_types=None, gamma=0.9450617049891935,grow_policy=None, importance_type=None,interaction_constraints=None, learning_rate=0.025181939608234893,max_bin=None, max_cat_threshold=None, max_cat_to_onehot=None,max_delta_step=None, max_depth=4, max_leaves=None,min_child_weight=2, monotone_constraints=None,multi_strategy=None, n_estimators=403, n_jobs=None,num_parallel_tree=None, random_state=None),
    "LightGBM_Tuned_Optima": lgb.LGBMRegressor(colsample_bytree=0.9562564045513104,learning_rate=0.08836732558896855, max_depth=4,min_child_samples=21, n_estimators=105, num_leaves=45,reg_alpha=0.4431230557718911, reg_lambda=1.0592541089500838,subsample=0.9333867867274527,verbose=-1)
}

# Initialize an empty DataFrame to store results
results_df_3 = pd.DataFrame(columns=["Model", "MAE", "MSE", "RMSE", "R2 Score"])

%%time
# Loop through each model, train it, evaluate it, and store results
for model_name, model in regression_models_3.items():
    model.fit(X_train, y_train)
    metrics = evaluate_model(model, X_test, y_test)
    metrics["Model"] = model_name  # Add model name for reference
    results_df_3 = pd.concat([results_df_3, pd.DataFrame([metrics])], ignore_index=True)

CPU times: total: 9.75 s
Wall time: 10.6 s

# Display the results DataFrame
# Tuned Models
results_df_3.sort_values(by="R2 Score", ascending=False)

# Display the results DataFrame
# Advanced Models
results_df_2.sort_values(by="R2 Score", ascending=False)

# Display the results DataFrame
# Regression Models
results_df.sort_values(by="R2 Score", ascending=False)

# Outlier handling
df7=df4[(np.abs(df4.select_dtypes(include=np.number).apply(zscore))<3).all(axis=1)] #drop over 3 standard deviations
count_outliers(df7)

price: 1345 outliers (8.67%)
rooms: 236 outliers (1.52%)
bathroom: 0 outliers (0.00%)
square_meters: 899 outliers (5.80%)
square_meters_price: 897 outliers (5.78%)

3377

df7.shape

(15511, 9)

df7.to_csv('df7_WITHOUT OUTLIERS 3SD_DATA.csv', index=False)  # Save a copy of data after outliers handling new approach

# Load data
data = df7.copy()

# Create dummy variables for categorical features with specified baseline categories
data = pd.get_dummies(data, columns=['real_state', 'neighborhood'], drop_first=False)
for feature, baseline in {'real_state': "flat", 'neighborhood': "Eixample"}.items():
        if f"{feature}_{baseline}" in data.columns:
            data.drop(columns=[f"{feature}_{baseline}"], inplace=True)

# Convert boolean columns to numeric (0 and 1)
bool_cols = data.select_dtypes(['bool']).columns
data[bool_cols] = data[bool_cols].astype(int)

univariate_numerical(data)

data.to_csv('df7_MODELING_DATA.csv', index=False)  # Save a copy of data ready for modeling

data.columns

Index(['price', 'rooms', 'bathroom', 'lift', 'terrace', 'square_meters',
       'square_meters_price', 'real_state_apartment', 'real_state_attic',
       'real_state_study', 'neighborhood_Ciutat Vella', 'neighborhood_Gràcia',
       'neighborhood_Horta- Guinardo', 'neighborhood_Les Corts',
       'neighborhood_Nou Barris', 'neighborhood_Sant Andreu',
       'neighborhood_Sant Martí', 'neighborhood_Sants-Montjuïc',
       'neighborhood_Sarria-Sant Gervasi'],
      dtype='object')

# Drop 'square_meter_price' from features
X = data.drop(columns=['price','square_meters_price'])
y = data['price']

# Train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Feature engineering
poly = PolynomialFeatures(degree=2, interaction_only=True, include_bias=False)
X_train_poly = poly.fit_transform(X_train)
X_test_poly = poly.transform(X_test)

# Standardization
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train_poly)
X_test_scaled = scaler.transform(X_test_poly)

# Stacking Regressor
base_models = [
    ('ridge', Ridge(alpha=1.0)),
    ('lasso', Lasso(alpha=0.1)),
    ('svr', SVR(kernel='rbf'))
]
meta_model = GradientBoostingRegressor(n_estimators=100, learning_rate=0.1)
stacking_model = StackingRegressor(estimators=base_models, final_estimator=meta_model)

# Cross-validation
cv_scores = cross_val_score(stacking_model, X_train_scaled, y_train, cv=5, scoring='r2')
print("Mean R2 Score from Cross Validation:", np.mean(cv_scores))

# Train and Evaluate
stacking_model.fit(X_train_scaled, y_train)
y_pred = stacking_model.predict(X_test_scaled)

Mean R2 Score from Cross Validation: 0.5837427472780874

target = "price"
features = [col for col in data.columns if col not in [target, "square_meters_price"]]

X = data[features]
y = data[target]

X.columns

Index(['rooms', 'bathroom', 'lift', 'terrace', 'square_meters',
       'real_state_apartment', 'real_state_attic', 'real_state_study',
       'neighborhood_Ciutat Vella', 'neighborhood_Gràcia',
       'neighborhood_Horta- Guinardo', 'neighborhood_Les Corts',
       'neighborhood_Nou Barris', 'neighborhood_Sant Andreu',
       'neighborhood_Sant Martí', 'neighborhood_Sants-Montjuïc',
       'neighborhood_Sarria-Sant Gervasi'],
      dtype='object')

# Apply Log Transformation to Reduce Skewness
y = np.log1p(y)

# Create Polynomial & Interaction Features
poly = PolynomialFeatures(degree=2, interaction_only=True, include_bias=False)
X_poly = poly.fit_transform(X)

# Train-Test Split
X_train, X_test, y_train, y_test = train_test_split(X_poly, y, test_size=0.2, random_state=42)

# Standardize Features
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Define Base Models
rf = RandomForestRegressor(n_estimators=300, max_depth=20, min_samples_split=5, random_state=42)
xgbr = xgb.XGBRegressor(n_estimators=300, max_depth=10, learning_rate=0.05, random_state=42)
lgbr = lgb.LGBMRegressor(n_estimators=300, max_depth=10, learning_rate=0.05, random_state=42, verbose=-1)

# Stacking Model
stacked_model = StackingRegressor(
    estimators=[("rf", rf), ("xgb", xgbr), ("lgb", lgbr)],
    final_estimator=xgb.XGBRegressor(n_estimators=100, learning_rate=0.1, max_depth=5, random_state=42)
)

# Train Model
stacked_model.fit(X_train, y_train)

# Evaluate Model
r2_score = stacked_model.score(X_test, y_test)
print(f"Improved R² Score: {r2_score:.4f}")

Improved R² Score: 0.6504

vif_series = pd.Series(
    [variance_inflation_factor(X.values, i) for i in range(X.shape[1])],
    index=X.columns,
    dtype=float,
)
print("Series before feature selection: \n\n{}\n".format(vif_series))

Series before feature selection: 

rooms                               11.126086
bathroom                            13.322090
lift                                 3.227964
terrace                              1.382929
square_meters                       15.947385
real_state_apartment                 1.135441
real_state_attic                     1.093636
real_state_study                     1.023852
neighborhood_Ciutat Vella            1.354277
neighborhood_Gràcia                  1.192324
neighborhood_Horta- Guinardo         1.095892
neighborhood_Les Corts               1.167469
neighborhood_Nou Barris              1.029682
neighborhood_Sant Andreu             1.059112
neighborhood_Sant Martí              1.192783
neighborhood_Sants-Montjuïc          1.162775
neighborhood_Sarria-Sant Gervasi     1.452696
dtype: float64

#Data load
inputs=pd.read_csv('df3_FATURE ENGINEERED_DATA.csv') # Original data, without missing values and feature "Unnamed"

data=inputs.copy()

# Outlier handling (drop values >3 standard deviations)
data = data[(np.abs(data.select_dtypes(include=np.number).apply(zscore)) < 3).all(axis=1)]

# Create dummy variables for categorical features with specified baseline categories
data = pd.get_dummies(data, columns=['real_state', 'neighborhood'], drop_first=False)
for feature, baseline in {'real_state': "flat", 'neighborhood': "Eixample"}.items():
        if f"{feature}_{baseline}" in data.columns:
            data.drop(columns=[f"{feature}_{baseline}"], inplace=True)

# Convert boolean columns to numeric (0 and 1)
bool_cols = data.select_dtypes(['bool']).columns
data[bool_cols] = data[bool_cols].astype(int)

target = "price"
outofmodel = ["square_meters_price", "rooms","bathroom"]
exclude_cols = [target] + outofmodel
features = [col for col in data.columns if col not in exclude_cols]

X = data[features]
y = data[target]

print(f'Original data features: {list(inputs.columns)}')
print(f'Modeling data features: {list(data.columns)}')
print(f'Output variable: {target}')
print(f'Input variables: {list(X.columns)}')

Original data features: ['price', 'rooms', 'bathroom', 'lift', 'terrace', 'square_meters', 'real_state', 'neighborhood', 'square_meters_price']
Modeling data features: ['price', 'rooms', 'bathroom', 'lift', 'terrace', 'square_meters', 'square_meters_price', 'real_state_apartment', 'real_state_attic', 'real_state_study', 'neighborhood_Ciutat Vella', 'neighborhood_Gràcia', 'neighborhood_Horta- Guinardo', 'neighborhood_Les Corts', 'neighborhood_Nou Barris', 'neighborhood_Sant Andreu', 'neighborhood_Sant Martí', 'neighborhood_Sants-Montjuïc', 'neighborhood_Sarria-Sant Gervasi']
Output variable: price
Input variables: ['lift', 'terrace', 'square_meters', 'real_state_apartment', 'real_state_attic', 'real_state_study', 'neighborhood_Ciutat Vella', 'neighborhood_Gràcia', 'neighborhood_Horta- Guinardo', 'neighborhood_Les Corts', 'neighborhood_Nou Barris', 'neighborhood_Sant Andreu', 'neighborhood_Sant Martí', 'neighborhood_Sants-Montjuïc', 'neighborhood_Sarria-Sant Gervasi']

%%time
# Apply Log Transformation to Reduce Skewness
y = np.log1p(y)

# Create Polynomial & Interaction Features
poly = PolynomialFeatures(degree=2, interaction_only=True, include_bias=False)
X_poly = poly.fit_transform(X)

# Train-Test Split
X_train, X_test, y_train, y_test = train_test_split(X_poly, y, test_size=0.2, random_state=42)

# Standardize Features
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Define Base Models
base_2 = [
    ('GradientBoosting_Tuned_2', GradientBoostingRegressor(min_samples_leaf=4, min_samples_split=10,random_state=42, subsample=0.8)),
    ('GradientBoosting_Optima', GradientBoostingRegressor(learning_rate=0.013201142547601463, max_depth=4,min_samples_leaf=7, min_samples_split=13,n_estimators=532, subsample=0.6777821390980873)),
    ('XGBoost_Tuned_Optima', xgb.XGBRegressor(base_score=None, booster=None, callbacks=None,colsample_bylevel=None, colsample_bynode=None,colsample_bytree=0.7494749285293014, device=None,early_stopping_rounds=None, enable_categorical=False,eval_metric=None, feature_types=None, gamma=0.9450617049891935,grow_policy=None, importance_type=None,interaction_constraints=None, learning_rate=0.025181939608234893,max_bin=None, max_cat_threshold=None, max_cat_to_onehot=None,max_delta_step=None, max_depth=4, max_leaves=None,min_child_weight=2, monotone_constraints=None,multi_strategy=None, n_estimators=403, n_jobs=None,num_parallel_tree=None, random_state=None))
]
# Define Meta Model
meta_2 = xgb.XGBRegressor(n_estimators=100, learning_rate=0.1, max_depth=5, random_state=42)
# Stacking Models
stacked_model_2 = StackingRegressor(estimators=base_2, final_estimator=meta_2)

# Train Model
stacked_model_2.fit(X_train, y_train)

# Evaluate Model
r2_score = stacked_model_2.score(X_test, y_test)
print(f"Improved R² Score: {r2_score:.4f}")

Improved R² Score: 0.6118
CPU times: total: 1min 59s
Wall time: 1min 49s

#Data load
inputs=pd.read_csv('df3_FATURE ENGINEERED_DATA.csv') # Original data, without missing values and feature "Unnamed"

data=inputs.copy()

# Outlier handling (drop values >3 standard deviations)
data = data[(np.abs(data.select_dtypes(include=np.number).apply(zscore)) < 3).all(axis=1)]

# Create dummy variables for categorical features with specified baseline categories
data = pd.get_dummies(data, columns=['real_state', 'neighborhood'], drop_first=False)
for feature, baseline in {'real_state': "flat", 'neighborhood': "Eixample"}.items():
        if f"{feature}_{baseline}" in data.columns:
            data.drop(columns=[f"{feature}_{baseline}"], inplace=True)

# Convert boolean columns to numeric (0 and 1)
bool_cols = data.select_dtypes(['bool']).columns
data[bool_cols] = data[bool_cols].astype(int)

target = "price"
outofmodel = ["square_meters_price"]
exclude_cols = [target] + outofmodel
features = [col for col in data.columns if col not in exclude_cols]

X = data[features]
y = data[target]

print(f'Original data features: {list(inputs.columns)}')
print(f'Modeling data features: {list(data.columns)}')
print(f'Output variable: {target}')
print(f'Input variables: {list(X.columns)}')

Original data features: ['price', 'rooms', 'bathroom', 'lift', 'terrace', 'square_meters', 'real_state', 'neighborhood', 'square_meters_price']
Modeling data features: ['price', 'rooms', 'bathroom', 'lift', 'terrace', 'square_meters', 'square_meters_price', 'real_state_apartment', 'real_state_attic', 'real_state_study', 'neighborhood_Ciutat Vella', 'neighborhood_Gràcia', 'neighborhood_Horta- Guinardo', 'neighborhood_Les Corts', 'neighborhood_Nou Barris', 'neighborhood_Sant Andreu', 'neighborhood_Sant Martí', 'neighborhood_Sants-Montjuïc', 'neighborhood_Sarria-Sant Gervasi']
Output variable: price
Input variables: ['rooms', 'bathroom', 'lift', 'terrace', 'square_meters', 'real_state_apartment', 'real_state_attic', 'real_state_study', 'neighborhood_Ciutat Vella', 'neighborhood_Gràcia', 'neighborhood_Horta- Guinardo', 'neighborhood_Les Corts', 'neighborhood_Nou Barris', 'neighborhood_Sant Andreu', 'neighborhood_Sant Martí', 'neighborhood_Sants-Montjuïc', 'neighborhood_Sarria-Sant Gervasi']

%%time
# Apply Log Transformation to Reduce Skewness
y = np.log1p(y)

# Create Polynomial & Interaction Features
poly = PolynomialFeatures(degree=2, interaction_only=True, include_bias=False)
X_poly = poly.fit_transform(X)

# Train-Test Split
X_train, X_test, y_train, y_test = train_test_split(X_poly, y, test_size=0.2, random_state=42)

# Standardize Features
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Define Base Models
base_final = [
    ('GradientBoosting_Tuned_2', GradientBoostingRegressor(min_samples_leaf=4, min_samples_split=10,random_state=42, subsample=0.8)),
    ('GradientBoosting_Optima', GradientBoostingRegressor(learning_rate=0.013201142547601463, max_depth=4,min_samples_leaf=7, min_samples_split=13,n_estimators=532, subsample=0.6777821390980873)),
    ('XGBoost_Tuned_Optima', xgb.XGBRegressor(base_score=None, booster=None, callbacks=None,colsample_bylevel=None, colsample_bynode=None,colsample_bytree=0.7494749285293014, device=None,early_stopping_rounds=None, enable_categorical=False,eval_metric=None, feature_types=None, gamma=0.9450617049891935,grow_policy=None, importance_type=None,interaction_constraints=None, learning_rate=0.025181939608234893,max_bin=None, max_cat_threshold=None, max_cat_to_onehot=None,max_delta_step=None, max_depth=4, max_leaves=None,min_child_weight=2, monotone_constraints=None,multi_strategy=None, n_estimators=403, n_jobs=None,num_parallel_tree=None, random_state=None))
]
# Define Meta Model
meta_final = xgb.XGBRegressor(base_score=None, booster=None, callbacks=None,colsample_bylevel=None, colsample_bynode=None,colsample_bytree=0.7494749285293014, device=None,early_stopping_rounds=None, enable_categorical=False,eval_metric=None, feature_types=None, gamma=0.9450617049891935,grow_policy=None, importance_type=None,interaction_constraints=None, learning_rate=0.025181939608234893,max_bin=None, max_cat_threshold=None, max_cat_to_onehot=None,max_delta_step=None, max_depth=4, max_leaves=None,min_child_weight=2, monotone_constraints=None,multi_strategy=None, n_estimators=403, n_jobs=None,num_parallel_tree=None, random_state=None)
# Stacking Models
stacked_model_final = StackingRegressor(estimators=base_final, final_estimator=meta_final)

# Train Model
stacked_model_final.fit(X_train, y_train)

# Evaluate Model
r2_score = stacked_model_final.score(X_test, y_test)
print(f"Improved R² Score: {r2_score:.4f}")

Improved R² Score: 0.6584
CPU times: total: 3min 20s
Wall time: 3min 24s

# Create models directory if it doesn't exist
os.makedirs("models", exist_ok=True)

# Get current date
current_date = datetime.datetime.now().strftime("%Y-%m-%d")

# Export the best model
file_name = f"models/stacked_model_at_{current_date}.pkl"
joblib.dump(stacked_model_final, file_name)

# Export feature transformers
scaler_name = f"models/scaler_at_{current_date}.pkl"
joblib.dump(scaler, scaler_name)

poly_name = f"models/poly_at_{current_date}.pkl"
joblib.dump(poly, poly_name)

print("Models saved successfully!")

Models saved successfully!

!jupyter nbconvert --to html PROJECT2_PYTHON.ipynb

C:\Users\otroc\AppData\Local\Programs\Python\Python313\Scripts\jupyter-nbconvert.EXE\__main__.py:4: DeprecationWarning: Parsing dates involving a day of month without a year specified is ambiguious
and fails to parse leap day. The default behavior will change in Python 3.15
to either always raise an exception or to use a different default year (TBD).
To avoid trouble, add a specific year to the input & format.
See https://github.com/python/cpython/issues/70647.
[NbConvertApp] Converting notebook PROJECT2_PYTHON.ipynb to html
[NbConvertApp] WARNING | Alternative text is missing on 19 image(s).
[NbConvertApp] Writing 4925911 bytes to PROJECT2_PYTHON.html

	count	unique	top	freq	mean	std	min	25%	50%	75%	max
Unnamed: 0	16376.0	NaN	NaN	NaN	8187.5	4727.488339	0.0	4093.75	8187.5	12281.25	16375.0
price	16376.0	NaN	NaN	NaN	1437.04586	1106.831419	320.0	875.0	1100.0	1514.0	15000.0
rooms	15966.0	NaN	NaN	NaN	2.421662	1.13863	0.0	1.884	2.111	3.0	10.754
bathroom	15989.0	NaN	NaN	NaN	1.504682	0.723192	0.9	1.0	1.037	2.0	8.0
lift	16376	2	True	11246	NaN	NaN	NaN	NaN	NaN	NaN	NaN
terrace	16376	2	False	12770	NaN	NaN	NaN	NaN	NaN	NaN	NaN
square_meters	15968.0	NaN	NaN	NaN	84.368874	47.486402	10.0	56.0855	72.748	95.0	679.0
real_state	15458	4	flat	12650	NaN	NaN	NaN	NaN	NaN	NaN	NaN
neighborhood	16376	10	Eixample	4795	NaN	NaN	NaN	NaN	NaN	NaN	NaN
square_meters_price	15937.0	NaN	NaN	NaN	17.73171	9.199731	4.549	12.777778	15.31	19.402	197.272

	rooms	count	int_prop	net_prop
0	1	1600	0.200000	0.097704
1	2	2608	0.326000	0.159257
2	3	2461	0.307625	0.150281
3	4	1061	0.132625	0.064790
4	5	232	0.029000	0.014167
5	6	28	0.003500	0.001710
6	7	5	0.000625	0.000305
7	8	0	0.000000	0.000000
8	9	2	0.000250	0.000122
9	10	3	0.000375	0.000183

	bathroom	count	int_prop	net_prop
0	1	4873	0.609125	0.297570
1	2	2742	0.342750	0.167440
2	3	421	0.052625	0.025708
3	4	121	0.015125	0.007389
4	5	41	0.005125	0.002504
5	6	9	0.001125	0.000550
6	7	1	0.000125	0.000061
7	8	2	0.000250	0.000122

	count	unique	top	freq	mean	std	min	25%	50%	75%	max
price	16376.0	NaN	NaN	NaN	1437.04586	1106.831419	320.0	875.0	1100.0	1514.0	15000.0
rooms	16376.0	NaN	NaN	NaN	2.447545	1.078844	1.0	2.0	2.0	3.0	11.0
bathroom	16376.0	NaN	NaN	NaN	1.495237	0.714843	1.0	1.0	1.0	2.0	8.0
lift	16376	2	True	11246	NaN	NaN	NaN	NaN	NaN	NaN	NaN
terrace	16376	2	False	12770	NaN	NaN	NaN	NaN	NaN	NaN	NaN
square_meters	16376.0	NaN	NaN	NaN	84.357363	47.454864	10.0	56.048	72.689	95.0	679.0
real_state	16376	4	flat	13568	NaN	NaN	NaN	NaN	NaN	NaN	NaN
neighborhood	16376	10	Eixample	4795	NaN	NaN	NaN	NaN	NaN	NaN	NaN
square_meters_price	16376.0	NaN	NaN	NaN	17.727253	9.185362	4.549	12.773723	15.315158	19.389167	197.272

	count	unique	top	freq	mean	std	min	25%	50%	75%	max
price	14269.0	NaN	NaN	NaN	1124.019833	371.448532	320.0	850.0	1000.0	1300.0	1975.0
rooms	14269.0	NaN	NaN	NaN	2.308291	0.939464	1.0	2.0	2.0	3.0	4.0
bathroom	14269.0	NaN	NaN	NaN	1.340949	0.474045	1.0	1.0	1.0	2.0	2.0
lift	14269	2	True	9753	NaN	NaN	NaN	NaN	NaN	NaN	NaN
terrace	14269	2	False	11384	NaN	NaN	NaN	NaN	NaN	NaN	NaN
square_meters	14269.0	NaN	NaN	NaN	73.41199	25.366439	10.313	55.0	70.0	87.264	135.66
real_state	14269	4	flat	12201	NaN	NaN	NaN	NaN	NaN	NaN	NaN
neighborhood	14269	10	Eixample	4154	NaN	NaN	NaN	NaN	NaN	NaN	NaN
square_meters_price	14269.0	NaN	NaN	NaN	16.1397	4.684702	6.001	12.676	15.0	18.681319	27.689297

1. Problem Definition¶

Objective¶

Problem Definition Consolidated Notes¶

2. Data Collection¶

Data Description¶

Importing necessary libraries¶

Loading the Dataset¶

Web Scraping¶

Property types¶

Data Collection Consolidated Notes¶

3. Data Preparation¶

Data Overview¶

Missing Value handling¶

Feature engineering¶

Outliers detection and treatment¶

Data Management¶

Data Preparation Consolidated Notes¶

4. Exploratory Data Analysis (EDA)¶

EDA Functions¶

Univariate Analysis¶

Bivariate Analysis¶

Exploratory Data Analysis Consolidated Notes¶

5. Modeling¶

Modeling Functions¶

Preparing data for modeling¶

Modeling Consolidated Notes¶

6. Evaluation¶

Regression Models¶

Feature Engineering¶

Advanced Regression Models¶

Model Tuning¶

Revisit¶

Final Modeling¶

Evaluation Consolidated Notes¶

7. Deployment¶

8. Monitoring and Maintenance¶

9. Communication and Reporting¶

	Unnamed: 0	price	rooms	bathroom	lift	terrace	square_meters	real_state	neighborhood	square_meters_price
0	0	750	3.0	1.0	True	False	60.0	flat	Horta- Guinardo	12.500000
1	1	770	2.0	1.0	True	False	59.0	flat	Sant Andreu	13.050847
2	2	1300	1.0	1.0	True	True	30.0	flat	Gràcia	43.333333
3	3	2800	1.0	1.0	True	True	70.0	flat	Ciutat Vella	40.000000
4	4	720	2.0	1.0	True	False	44.0	flat	Sant Andreu	16.363636

	Unnamed: 0	price	rooms	bathroom	lift	terrace	square_meters	real_state	neighborhood	square_meters_price
16371	16371	950	1.982	0.957	True	False	60.701	flat	Sarria-Sant Gervasi	13.174
16372	16372	825	1.086	0.961	True	False	47.224	flat	Eixample	14.893
16373	16373	1200	4.195	1.957	True	False	116.100	flat	Les Corts	10.746
16374	16374	1100	2.899	2.155	False	False	57.805	flat	Sant Martí	NaN
16375	16375	850	2.127	1.024	True	False	58.503	flat	Eixample	15.390

	Unnamed: 0	price	rooms	bathroom	lift	terrace	square_meters	real_state	neighborhood	square_meters_price
5205	5205	1350	4.000	2.000	True	False	120.000	flat	Sarria-Sant Gervasi	11.250000
4992	4992	950	3.000	1.000	True	False	76.000	attic	Horta- Guinardo	12.500000
1582	1582	1650	4.000	2.000	True	False	135.000	flat	Sarria-Sant Gervasi	12.222222
7434	7434	1350	3.000	2.000	True	False	80.000	flat	Eixample	16.875000
14345	14345	2250	2.708	1.813	True	True	175.068	flat	Eixample	14.308000
8638	8638	950	2.193	0.994	False	False	58.671	flat	Sarria-Sant Gervasi	16.291000
2187	2187	725	1.000	1.000	True	False	70.000	flat	Ciutat Vella	10.357143
7954	7954	1100	1.000	1.000	True	False	57.000	flat	Eixample	19.298246
7441	7441	700	1.000	1.000	False	False	33.000	flat	Ciutat Vella	21.212121
4555	4555	1600	2.000	1.000	False	False	75.000	flat	Eixample	21.333333
1926	1926	990	4.000	1.000	False	False	75.000	flat	Eixample	13.200000
11446	11446	800	2.820	0.906	False	False	82.412	flat	Sarria-Sant Gervasi	10.680000
2321	2321	990	2.000	2.000	True	False	73.000	flat	Gràcia	13.561644
8559	8559	1350	2.080	NaN	True	False	63.588	flat	Ciutat Vella	20.524000
2028	2028	1175	4.000	2.000	True	False	90.000	flat	Eixample	13.055556
5207	5207	720	2.000	1.000	False	False	53.000	flat	Ciutat Vella	13.584906
2951	2951	1050	2.000	2.000	True	False	65.000	flat	Sant Martí	16.153846
5535	5535	1850	2.000	2.000	True	False	144.000	apartment	Ciutat Vella	12.847222
1374	1374	2800	4.000	3.000	True	True	175.000	NaN	Sarria-Sant Gervasi	16.000000
9272	9272	1650	3.228	2.122	True	False	88.468	flat	Sants-Montjuïc	16.974000

	Null Count	Null Percentage
Unnamed: 0	0	0.00
price	0	0.00
rooms	410	2.50
bathroom	387	2.36
lift	0	0.00
terrace	0	0.00
square_meters	408	2.49
real_state	918	5.61
neighborhood	0	0.00
square_meters_price	439	2.68

	Unnamed: 0	price	rooms	bathroom	lift	terrace	square_meters	real_state	neighborhood	square_meters_price
8748	8748	1300	4.392	1.980	True	False	NaN	flat	Eixample	NaN
8784	8784	850	0.950	0.995	False	False	NaN	flat	Sants-Montjuïc	NaN
9118	9118	925	2.175	0.924	True	False	NaN	flat	Gràcia	NaN
9321	9321	895	NaN	1.877	True	False	NaN	flat	Sants-Montjuïc	NaN
9442	9442	800	0.924	1.092	False	False	NaN	flat	Horta- Guinardo	NaN
9519	9519	995	2.858	2.161	False	True	NaN	flat	Eixample	NaN
10167	10167	1218	3.686	2.140	True	False	NaN	flat	Sarria-Sant Gervasi	NaN
11180	11180	600	NaN	0.917	True	True	NaN	flat	Sants-Montjuïc	NaN
11496	11496	945	1.009	0.962	True	True	NaN	attic	Sarria-Sant Gervasi	NaN
11959	11959	850	3.039	NaN	True	False	NaN	flat	Horta- Guinardo	NaN
12782	12782	1000	3.226	0.965	False	False	NaN	flat	Eixample	NaN
13086	13086	790	3.637	0.963	True	True	NaN	flat	Eixample	NaN
13189	13189	5300	NaN	4.695	False	True	NaN	flat	Les Corts	NaN
13401	13401	850	0.973	0.917	True	False	NaN	apartment	Eixample	NaN
13817	13817	1100	2.937	2.169	False	False	NaN	flat	Gràcia	NaN
14693	14693	740	1.068	0.949	True	False	NaN	flat	Eixample	NaN
15761	15761	1140	2.179	0.942	True	False	NaN	attic	Gràcia	NaN
16118	16118	1500	3.255	1.986	True	False	NaN	flat	Sarria-Sant Gervasi	NaN
16181	16181	800	1.050	1.082	True	False	NaN	flat	Gràcia	NaN

	count	mean	std	min	25%	50%	75%	max
price	12201.0	1097.272601	344.695856	320.000	850.000	1000.000	1250.000000	1975.000000
rooms	12201.0	2.384067	0.930198	1.000	2.000	2.000	3.000000	4.000000
bathroom	12201.0	1.353004	0.477923	1.000	1.000	1.000	2.000000	2.000000
square_meters	12201.0	74.623287	24.862834	13.181	56.559	70.902	88.388000	135.660000
square_meters_price	12201.0	15.435230	4.183763	6.001	12.465	14.516	17.647059	27.689297

	count	mean	std	min	25%	50%	75%	max
Unnamed: 0	12650.0	8038.174625	4750.342568	0.000000	3887.250000	7965.5000	12162.75000	16375.000
price	12650.0	1311.412490	917.152962	320.000000	865.000000	1050.0000	1352.00000	15000.000
rooms	12351.0	2.551887	1.091363	0.000000	2.000000	2.7380	3.03600	10.754
bathroom	12380.0	1.509471	0.715738	0.900000	1.000000	1.0405	2.00000	8.000
square_meters	12352.0	85.484011	45.657731	10.540000	59.000000	74.7985	95.64450	679.000
square_meters_price	12322.0	15.707694	5.333934	5.555556	12.437625	14.5000	17.67775	103.176

	count	mean	std	min	25%	50%	75%	max
price	4154.0	1186.479779	376.948534	425.000	900.00000	1100.0000	1400.0000	1975.000000
rooms	4154.0	2.403707	0.940306	1.000	2.00000	2.0000	3.0000	4.000000
bathroom	4154.0	1.391911	0.488236	1.000	1.00000	1.0000	2.0000	2.000000
square_meters	4154.0	76.669525	25.506765	16.197	58.00000	74.0505	90.2625	135.660000
square_meters_price	4154.0	16.357695	4.795151	6.074	12.79825	15.0455	19.1155	27.689297

	variable1	variable2	correlation	corr_lvl
3	price	square_meters	0.651214	Moderate
8	rooms	square_meters	0.635150	Moderate
13	bathroom	square_meters	0.608319	Moderate
2	price	bathroom	0.503768	Moderate
7	rooms	bathroom	0.451065	Low
9	rooms	square_meters_price	-0.416305	Low
19	square_meters	square_meters_price	-0.391874	Low
4	price	square_meters_price	0.381253	Low
1	price	rooms	0.304009	Low
14	bathroom	square_meters_price	-0.111716	Negligible

	const	rooms	bathroom	lift	terrace	square_meters	square_meters_price	real_state_flat	neighborhood_Eixample	neighborhood_Horta- Guinardo
16047	1.0	2	1	1	0	0.163420	0.503709	1	0	0
10334	1.0	1	1	1	0	-1.500990	1.774314	1	1	0
10144	1.0	2	1	0	0	-1.953426	0.850089	1	0	0
8401	1.0	3	1	1	1	1.666115	-0.559885	1	0	0
2041	1.0	3	1	0	1	-0.098884	-1.895277	1	0	1

	Model	MAE	MSE	RMSE	R2 Score
4	Random Forest	39.785481	4165.852534	64.543416	0.970178
3	Decision Tree	50.995982	7282.203392	85.335827	0.947870
2	Ridge Regression	67.054647	9179.684362	95.810669	0.934286
0	Linear Regression	67.057076	9180.541068	95.815140	0.934280
1	Lasso Regression	67.493485	9249.945144	96.176635	0.933783
5	K-Nearest Neighbors	74.951133	11475.952189	107.125871	0.917848
6	Support Vector Regressor	98.720296	23091.488357	151.958838	0.834697

	Model	MAE	MSE	RMSE	R2 Score
4	Random Forest	39.785481	4165.852534	64.543416	0.970178
3	Decision Tree	50.995982	7282.203392	85.335827	0.947870
2	Ridge Regression	67.054647	9179.684362	95.810669	0.934286
0	Linear Regression	67.057076	9180.541068	95.815140	0.934280
1	Lasso Regression	67.493485	9249.945144	96.176635	0.933783
5	K-Nearest Neighbors	74.951133	11475.952189	107.125871	0.917848
6	Support Vector Regressor	98.720296	23091.488357	151.958838	0.834697

	Model	MAE	MSE	RMSE	R2 Score
4	Random Forest	39.785481	4165.852534	64.543416	0.970178
3	Decision Tree	50.995982	7282.203392	85.335827	0.947870
2	Ridge Regression	67.054647	9179.684362	95.810669	0.934286
0	Linear Regression	67.057076	9180.541068	95.815140	0.934280
1	Lasso Regression	67.493485	9249.945144	96.176635	0.933783
5	K-Nearest Neighbors	74.951133	11475.952189	107.125871	0.917848
6	Support Vector Regressor	98.720296	23091.488357	151.958838	0.834697

	Model	MAE	MSE	RMSE	R2 Score
4	Random Forest	39.785481	4165.852534	64.543416	0.970178
3	Decision Tree	50.995982	7282.203392	85.335827	0.947870
2	Ridge Regression	67.054647	9179.684362	95.810669	0.934286
0	Linear Regression	67.057076	9180.541068	95.815140	0.934280
1	Lasso Regression	67.493485	9249.945144	96.176635	0.933783
5	K-Nearest Neighbors	74.951133	11475.952189	107.125871	0.917848
6	Support Vector Regressor	98.720296	23091.488357	151.958838	0.834697

	Model	MAE	MSE	RMSE	R2 Score
0	Linear Regression	192.829593	62956.269056	250.910879	0.549322
2	Ridge Regression	192.833577	62957.371541	250.913076	0.549314
1	Lasso Regression	193.843038	63504.450907	252.000895	0.545397
4	Random Forest	188.532068	64705.626597	254.373007	0.536799
5	K-Nearest Neighbors	193.531091	67397.543929	259.610369	0.517528
6	Support Vector Regressor	210.787271	86373.521736	293.893725	0.381687
3	Decision Tree	219.420021	95376.122393	308.830249	0.317241

	Model	MAE	MSE	RMSE	R2 Score
0	Linear Regression	197.545690	65051.360633	255.051682	0.534324
2	Ridge Regression	197.554341	65051.439986	255.051838	0.534323
1	Lasso Regression	198.916759	65589.695703	256.104853	0.530470
5	K-Nearest Neighbors	198.173137	69939.496099	264.460765	0.499331
4	Random Forest	198.968127	71029.109970	266.512870	0.491531
6	Support Vector Regressor	211.486036	86079.067618	293.392344	0.383795
3	Decision Tree	227.006181	98680.824283	314.135041	0.293584

	Model	MAE	MSE	RMSE	R2 Score
2	Ridge Regression	203.954404	68258.459986	261.263201	0.511365
0	Linear Regression	203.946460	68259.489536	261.265171	0.511358
1	Lasso Regression	204.980574	68760.982886	262.223155	0.507768
5	K-Nearest Neighbors	205.304975	74808.167353	273.510818	0.464479
4	Random Forest	203.990067	74902.742779	273.683655	0.463802
6	Support Vector Regressor	216.002731	89473.683618	299.121520	0.359494
3	Decision Tree	235.145948	106969.349675	327.061691	0.234250

	Model	MAE	MSE	RMSE	R2 Score
2	GradientBoosting_Tuned_1	190.979607	63554.668646	252.100513	0.545038
4	LightGBM_Tuned_1	191.308692	63653.691737	252.296833	0.544329
3	XGBoost_Tuned_1	191.172298	63903.217757	252.790858	0.542543
1	RandomForest_Tuned_1	192.255939	64194.833169	253.366993	0.540455
5	NeuralNetwork(MLP)	201.536209	66683.063761	258.230641	0.522643
0	DecisionTree_Tuned_1	197.879923	70119.813941	264.801461	0.498041

	Model	MAE	MSE	RMSE	R2 Score
4	XGBoost_Tuned_Optima	190.967571	62720.926919	250.441464	0.551006
3	GradientBoosting_Optima	190.906116	62859.987800	250.718942	0.550011
0	GradientBoosting_Tuned_2	191.385545	62994.960983	250.987970	0.549045
5	LightGBM_Tuned_Optima	191.011681	63051.358720	251.100296	0.548641
1	XGBoost_Tuned_2	191.250406	63130.225737	251.257290	0.548076
2	LightGBM_Tuned_2	191.907873	63205.786577	251.407610	0.547535